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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant societal issues and concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -1.08
    GraphicsUnit
    -1.06
     ModelExpression
    -0.95
     مرئيه
    -0.95
    elemField
    -0.95
    WithIOException
    -0.94
    setVerticalGroup
    -0.91
    ArgsConstructor
    -0.86
    HtmlAttribute
    -0.86
    awtextra
    -0.84
    POSITIVE LOGITS
     regardless
    0.58
    Regardless
    0.54
     but
    0.52
     Regardless
    0.49
     irrespective
    0.48
    Any
    0.45
    元々
    0.44
     any
    0.44
    无论
    0.43
    regardless
    0.43
    Act Density 0.373%

    No Known Activations