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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a pause or delay in speech

    oai_token-act-pair · gpt-3.5-turbo

    statements that suggest hesitation or calls for attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.77
    imum
    -0.72
    aturday
    -0.69
    ertain
    -0.69
    cellent
    -0.67
    erate
    -0.66
    nesota
    -0.64
    Ö¼
    -0.63
    bern
    -0.63
    olute
    -0.63
    POSITIVE LOGITS
     WHY
    0.84
     forgot
    0.78
     THERE
    0.76
     Didn
    0.74
     Reincarn
    0.71
     Isn
    0.68
    ?!
    0.67
     kidding
    0.67
     WHAT
    0.66
    !?
    0.66
    Act Density 0.106%

    No Known Activations