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

    Neuronpedia

    INDEX
    Explanations

    direct speech with quotations

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks indicating spoken or quoted dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prec
    -0.82
     prelim
    -0.78
     pacing
    -0.77
     altar
    -0.73
     halfway
    -0.72
     streaming
    -0.72
     priesthood
    -0.72
     studio
    -0.70
     ranking
    -0.70
     pyramid
    -0.70
    POSITIVE LOGITS
    Really
    1.20
    We
    1.17
    quickShipAvailable
    1.15
    Certainly
    1.14
    I
    1.12
    What
    1.11
    Very
    1.10
    Quite
    1.09
    You
    1.09
    It
    1.09
    Act Density 0.096%

    No Known Activations