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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms indicating negation or warning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.96
    enumi
    -0.83
    dymyr
    -0.80
    kloped
    -0.80
     EconPapers
    -0.75
    клопе
    -0.74
    writeField
    -0.72
    enderror
    -0.72
    หวัด
    -0.72
    DoubleQuotes
    -0.69
    POSITIVE LOGITS
     NOT
    1.07
     ONLY
    1.04
     BOTH
    1.01
     ANY
    0.97
     MUST
    0.95
     VERY
    0.93
    ONLY
    0.92
     ANYONE
    0.91
     SAME
    0.91
     HUGE
    0.91
    Act Density 0.096%

    No Known Activations