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

    Neuronpedia

    INDEX
    Explanations

    names of individuals involved in criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mathemat
    -0.74
    izoph
    -0.70
    soDeliveryDate
    -0.70
    Temperature
    -0.67
     favourable
    -0.67
     hemisphere
    -0.64
     patience
    -0.63
     pathological
    -0.63
    translation
    -0.63
    Compared
    -0.63
    POSITIVE LOGITS
     Jr
    1.44
     III
    1.18
     Sr
    1.07
    vich
    0.94
    burgh
    0.93
    iewicz
    0.91
    baum
    0.91
     aka
    0.90
    owski
    0.89
    icz
    0.88
    Act Density 0.250%

    No Known Activations