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

    Neuronpedia

    INDEX
    Explanations

    mentions of associations, awards, and nominations in a text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    lasses
    -0.82
    =-=-=-=-=-=-=-=-
    -0.73
    stocks
    -0.72
    gone
    -0.72
    haven
    -0.66
    tro
    -0.66
    adow
    -0.65
    castle
    -0.65
    lass
    -0.63
    falls
    -0.63
    POSITIVE LOGITS
    UTH
    0.84
     membership
    0.80
    uthor
    0.77
    eer
    0.75
     Association
    0.75
    auga
    0.72
     Agreement
    0.72
     Membership
    0.71
     Board
    0.70
    eers
    0.70
    Act Density 7.851%

    No Known Activations