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

    Neuronpedia

    INDEX
    Explanations

    descriptions of suspects in a crime report

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    livion
    -0.72
     cures
    -0.68
    ifference
    -0.67
     truths
    -0.67
    fters
    -0.67
    erve
    -0.66
    ossom
    -0.65
    absor
    -0.65
    imer
    -0.63
    onut
    -0.62
    POSITIVE LOGITS
     Caucasian
    1.13
     juveniles
    0.87
     Caucas
    0.86
     Faw
    0.80
     dressed
    0.80
     unknown
    0.79
     surn
    0.79
     unidentified
    0.78
     unspecified
    0.78
    aucas
    0.78
    Act Density 0.152%

    No Known Activations