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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate contrasting circumstances or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '
    -0.61
     Chartres
    -0.56
    יצד
    -0.56
    WA
    -0.56
     minerals
    -0.53
    ћа
    -0.53
     lika
    -0.53
     Skinner
    -0.49
     Torino
    -0.49
    hassee
    -0.48
    POSITIVE LOGITS
    ostante
    1.74
     despite
    1.48
     Despite
    1.40
    despite
    1.35
     Trotz
    1.35
    Despite
    1.34
     nonostante
    1.30
    Trotz
    1.29
     Malgré
    1.29
     spite
    1.28
    Act Density 0.085%

    No Known Activations