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

    Neuronpedia

    INDEX
    Explanations

    various expressions of multiplicative relationships or growth rates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.61
     hysteresis
    -0.57
    arpur
    -0.54
     pocos
    -0.54
     tremors
    -0.53
    äs
    -0.53
    ılı
    -0.52
    Bronnen
    -0.52
    GetResponse
    -0.52
     Corso
    -0.51
    POSITIVE LOGITS
    Twice
    1.06
    twice
    1.02
     Twice
    0.93
     thrice
    0.91
     twice
    0.91
     triple
    0.88
     double
    0.87
     TWICE
    0.86
     quadruple
    0.86
     ganger
    0.83
    Act Density 0.583%

    No Known Activations