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

    Neuronpedia

    INDEX
    Explanations

    questions or statements expressing uncertainty or speculation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ciating
    -0.68
    ertodd
    -0.66
    herent
    -0.58
    phrine
    -0.58
     Vital
    -0.54
    umsy
    -0.54
    cakes
    -0.54
    etsk
    -0.54
    ACTION
    -0.52
    PRESS
    -0.52
    POSITIVE LOGITS
    ?),
    0.66
    ?!
    0.58
    ?).
    0.58
    ?:
    0.57
     darn
    0.56
    ?)
    0.56
     suppose
    0.56
     wonder
    0.55
     chalk
    0.53
     prest
    0.53
    Act Density 7.734%

    No Known Activations