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

    Neuronpedia

    INDEX
    Explanations

    quotations and direct speech

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     increa
    -2.35
     reluct
    -2.25
     affor
    -2.20
     impra
    -2.18
     guarante
    -2.16
     encomp
    -2.16
     disagre
    -2.11
     suscep
    -2.11
     fuf
    -2.07
     scrat
    -2.05
    POSITIVE LOGITS
    I
    0.89
    If
    0.82
    “
    0.80
    My
    0.80
    You
    0.79
    There
    0.78
     …
    0.78
    Let
    0.78
    ()))
    0.77
    No
    0.76
    Act Density 0.297%

    No Known Activations