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

    Neuronpedia

    INDEX
    Explanations

    terms related to controversy and scandals

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Hagen
    -0.69
     sĩ
    -0.66
    เต
    -0.65
     Hicks
    -0.60
     Genes
    -0.60
     H
    -0.57
     Hải
    -0.56
    ",
    -0.55
    bekah
    -0.55
    fresh
    -0.54
    POSITIVE LOGITS
    versial
    1.35
     controversies
    1.34
     controversy
    1.29
     Controversy
    1.24
     controver
    1.14
    ViewFeatures
    1.13
     controversial
    1.09
    Controversy
    1.09
     controversi
    1.06
     Contro
    1.02
    Act Density 0.006%

    No Known Activations