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

    Neuronpedia

    INDEX
    Explanations

    timestamps indicating a point in time in text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     favour
    -0.73
    adr
    -0.69
    tnc
    -0.67
    #$
    -0.67
    rouse
    -0.63
     favor
    -0.62
    natureconservancy
    -0.61
    uras
    -0.61
    vt
    -0.61
    ËĪ
    -0.61
    POSITIVE LOGITS
     versions
    0.85
    noon
    0.85
     editions
    0.84
     revelations
    0.79
    etheless
    0.76
     indications
    0.75
     analyses
    0.72
     Accounts
    0.72
     translations
    0.71
     Stories
    0.70
    Act Density 0.046%

    No Known Activations