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

    Neuronpedia

    INDEX
    Explanations

    financial transactions or exchanges

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.73
    worldly
    -0.66
    :(
    -0.65
    ,-
    -0.63
    ,—
    -0.63
    ,...
    -0.58
    ,.
    -0.58
    :
    -0.56
    .—
    -0.55
    Reward
    -0.55
    POSITIVE LOGITS
     respectively
    0.79
     which
    0.78
     whose
    0.75
     who
    0.73
     whom
    0.71
    whose
    0.67
     according
    0.66
     whereby
    0.63
     namely
    0.63
    who
    0.62
    Act Density 0.323%

    No Known Activations