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

    Neuronpedia

    INDEX
    Explanations

    negative indicators of bias or discrimination

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    UIControlState
    -0.60
    ודם
    -0.60
    ESTE
    -0.60
    бливості
    -0.59
     Adair
    -0.59
    Demografie
    -0.58
     Swann
    -0.58
     Kimmel
    -0.58
     civilised
    -0.58
     sớm
    -0.57
    POSITIVE LOGITS
    LookAnd
    0.90
    —
    0.89
    parsedMessage
    0.83
     XNUMX
    0.75
     Stande
    0.74
    出版年
    0.74
    RenderAtEndOf
    0.73
     *)__
    0.72
     mettant
    0.70
     pérd
    0.70
    Act Density 0.002%

    No Known Activations