Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to user experience improvement and environmental benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Non-English text and numbers

    np_acts-logits-general · gemini-2.0-flash

    Waffles, polymerase complex

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates for text that follows a beginning-of-sentence marker, particularly focusing on formal, authoritative information presented in complete sentences.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @au75
    New Auto-Interp
    Negative Logits
     wherewith
    -0.69
    tvguidetime
    -0.63
    Totally
    -0.60
     awfully
    -0.59
     terribly
    -0.57
     Totally
    -0.56
     thingy
    -0.55
     geni
    -0.55
     bête
    -0.55
     terrific
    -0.54
    POSITIVE LOGITS
     تانيه
    0.82
    Geplaatst
    0.79
    بوابة
    0.78
     ligiloj
    0.78
    Билгалдахарш
    0.78
    💼
    0.76
    存于互联网档案馆
    0.75
    Collegamenti
    0.73
     propOrder
    0.73
     وتسجيلات
    0.72
    Act Density 0.016%

    No Known Activations