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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    the presence of repeated punctuation marks, specifically commas and possibly parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hens
    -0.72
    20439
    -0.69
    ability
    -0.65
    inar
    -0.63
    Nap
    -0.61
     outgoing
    -0.58
    CLE
    -0.58
    herent
    -0.56
    hed
    -0.56
    estate
    -0.56
    POSITIVE LOGITS
     anecd
    0.78
     albeit
    0.72
    uyomi
    0.72
     lest
    0.69
    _>
    0.68
    bet
    0.67
    perhaps
    0.67
     although
    0.67
     alas
    0.67
    but
    0.63
    Act Density 0.347%

    No Known Activations