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

    Neuronpedia

    INDEX
    Explanations

    contexts highlighting contrast or contradictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hassee
    -0.58
    יצד
    -0.56
    '
    -0.55
     Chartres
    -0.55
    jazdu
    -0.55
     initComponents
    -0.53
    конец
    -0.52
     οποία
    -0.51
     Rois
    -0.51
    WA
    -0.51
    POSITIVE LOGITS
    ostante
    1.68
     despite
    1.34
     Despite
    1.30
     Trotz
    1.24
    Despite
    1.24
     Malgré
    1.23
    despite
    1.23
     nonostante
    1.23
    Trotz
    1.21
     spite
    1.17
    Act Density 0.073%

    No Known Activations