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

    Neuronpedia

    INDEX
    Explanations

    questions and uncertainties expressed in a narrative or dialogue format

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    tein
    -0.81
     Jinn
    -0.73
     Nightmare
    -0.66
     vain
    -0.65
     Bom
    -0.64
    mania
    -0.62
     Niet
    -0.60
    espie
    -0.60
     Compan
    -0.59
     composing
    -0.59
    POSITIVE LOGITS
    everal
    0.80
    aternity
    0.70
    endale
    0.69
    abouts
    0.69
    ileged
    0.69
    othal
    0.68
     occasions
    0.68
    vice
    0.68
    uable
    0.67
    omen
    0.67
    Act Density 0.923%

    No Known Activations