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

    Neuronpedia

    INDEX
    Explanations

    terms related to political, social, and economic structures and dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     picado
    -0.55
     singola
    -0.54
     katze
    -0.53
     Goed
    -0.53
    ogli
    -0.53
    TestingModule
    -0.52
     Rady
    -0.51
     houſe
    -0.50
    outSlope
    -0.49
     poffe
    -0.49
    POSITIVE LOGITS
    Personendaten
    0.86
    hwar
    0.69
    thâu
    0.64
     hablando
    0.64
     dAtA
    0.64
    nological
    0.63
    DoubleQuotes
    0.62
    CloseOperation
    0.62
    localScale
    0.61
     للاسماء
    0.61
    Act Density 0.671%

    No Known Activations