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

    Neuronpedia

    INDEX
    Explanations

    phrases related to extreme behavior and its implications in a societal context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.91
     Roskov
    -0.88
    IndentedString
    -0.86
    expandindo
    -0.81
     Majefty
    -0.78
     CreateTagHelper
    -0.77
    MLLoader
    -0.77
     ModelExpression
    -0.75
    DeleteBehavior
    -0.72
    Décès
    -0.72
    POSITIVE LOGITS
    中略
    0.48
     rédu
    0.47
    ungsver
    0.45
     calendriers
    0.45
    腺
    0.45
    enser
    0.44
     limitée
    0.44
     kalau
    0.44
    …
    0.44
    ……
    0.43
    Act Density 0.097%

    No Known Activations