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

    Neuronpedia

    INDEX
    Explanations

    quotations and dialogue tags

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "he" repeatedly used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Maid
    -0.67
    fit
    -0.63
    BALL
    -0.61
     hindsight
    -0.61
    anking
    -0.60
     interfering
    -0.60
    rocket
    -0.60
    iries
    -0.59
    âĻ¦
    -0.59
    split
    -0.58
    POSITIVE LOGITS
    'd
    1.03
     wrote
    0.97
    'll
    0.93
     lamented
    0.86
     said
    0.85
     joked
    0.83
     tweeted
    0.82
    mos
    0.82
    said
    0.79
     says
    0.76
    Act Density 0.191%

    No Known Activations