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

    Neuronpedia

    INDEX
    Explanations

    negations related to personal experiences or abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adpleegd
    -0.82
     Thales
    -0.80
    setSource
    -0.78
     Gibbs
    -0.76
     Weiss
    -0.76
    ebe
    -0.74
     PACE
    -0.72
    tır
    -0.72
     merce
    -0.71
     _('
    -0.71
    POSITIVE LOGITS
     isn
    1.34
     wasn
    1.26
     weren
    1.25
     Wasn
    1.22
     aren
    1.21
     didn
    1.19
     shouldn
    1.17
     mustn
    1.17
     Isn
    1.17
    doesn
    1.15
    Act Density 0.074%

    No Known Activations