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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal or law enforcement scenarios and personal struggles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Interested
    -0.76
     Contains
    -0.75
    ĸļ
    -0.69
    yip
    -0.67
    VID
    -0.65
    actionDate
    -0.65
    existent
    -0.65
     Speaking
    -0.64
    peak
    -0.63
    paren
    -0.63
    POSITIVE LOGITS
     retreated
    1.43
     reverted
    1.42
     proceeded
    1.41
     withdrew
    1.33
     promptly
    1.28
     returned
    1.27
     resorted
    1.25
     resumed
    1.23
     went
    1.22
     fled
    1.20
    Act Density 0.430%

    No Known Activations