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

    Neuronpedia

    INDEX
    Explanations

    emotionally charged expressions and symbols

    oai_token-act-pair · gpt-3.5-turbo

    uncommon or special characters used in digital contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gillespie
    -0.78
     gloom
    -0.69
     Sidd
    -0.68
     Franch
    -0.67
    ioned
    -0.65
     Sind
    -0.63
     Quadro
    -0.63
     Sle
    -0.63
     Abyssal
    -0.63
     Tid
    -0.62
    POSITIVE LOGITS
    İ
    1.60
    Ĵ
    1.60
    Į
    1.57
    ĵ
    1.55
    Ķ
    1.48
    ĻĤ
    1.46
    ¥ŀ
    1.43
    į
    1.40
    IJ
    1.38
    ¦
    1.37
    Act Density 0.012%

    No Known Activations