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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal processes and political affairs

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     unwitting
    -0.86
    drawn
    -0.77
     disbelief
    -0.77
     fict
    -0.77
    FUL
    -0.75
     ripe
    -0.74
     moratorium
    -0.74
     mosqu
    -0.74
     skim
    -0.73
     calendars
    -0.73
    POSITIVE LOGITS
    ript
    0.89
    Byte
    0.87
    phe
    0.86
    anski
    0.84
    Entry
    0.76
    byte
    0.76
    zinski
    0.75
    bash
    0.74
    byn
    0.72
    ious
    0.71
    Act Density 1.589%

    No Known Activations