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

    Neuronpedia

    INDEX
    Explanations

    references to independent or partisan ideologies and their influences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dalamnya
    -0.58
    alcool
    -0.50
    antaranya
    -0.49
     décadas
    -0.48
     honneur
    -0.47
     paciencia
    -0.47
     transportasi
    -0.46
     kyse
    -0.46
     fueran
    -0.46
     vuel
    -0.45
    POSITIVE LOGITS
    __*/
    0.60
     private
    0.60
     oral
    0.58
     verbal
    0.58
    jspb
    0.57
     Catholic
    0.56
     Mexican
    0.55
     pure
    0.55
     Belgian
    0.55
     German
    0.54
    Act Density 6.790%

    No Known Activations