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

    Neuronpedia

    INDEX
    Explanations

    negative variations of the words "to be" and their negations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -1.01
    Personensuche
    -0.95
     betweenstory
    -0.86
     ModelExpression
    -0.84
     propOrder
    -0.83
    MessageOf
    -0.79
    örté
    -0.78
     jspb
    -0.74
    Ответы
    -0.73
    haven
    -0.73
    POSITIVE LOGITS
     is
    0.97
     !=
    0.59
    is
    0.58
     S
    0.56
    S
    0.56
     Is
    0.55
     IS
    0.55
     was
    0.54
     является
    0.53
     P
    0.53
    Act Density 0.122%

    No Known Activations