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

    Neuronpedia

    INDEX
    Explanations

    the negation of statements or concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Personensuche
    -1.15
    expandindo
    -1.09
    ViewFeatures
    -1.05
    jsii
    -1.02
     '\\;'
    -1.00
     ModelExpression
    -0.99
    ⓧ
    -0.98
     kasarigan
    -0.97
    MessageTagHelper
    -0.93
    #![
    -0.92
    POSITIVE LOGITS
     kann
    0.63
    väg
    0.60
     can
    0.56
     puede
    0.56
    біль
    0.55
     might
    0.54
     saja
    0.54
     bornes
    0.54
     may
    0.52
     عد
    0.52
    Act Density 0.066%

    No Known Activations