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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and descriptors related to identity and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endregion
    -0.72
    ঐ
    -0.63
    ectomy
    -0.59
     столько
    -0.56
     <<<<<<<<<<<<<<
    -0.56
    Шаг
    -0.56
     sangu
    -0.56
    homePage
    -0.55
     Bateman
    -0.55
     disesuaikan
    -0.55
    POSITIVE LOGITS
     در
    1.52
    در
    1.34
     يتيمه
    1.16
     با
    0.91
    LoggerFactory
    0.84
    EndInit
    0.82
     از
    0.82
    دانشنامهٔ
    0.82
     useStyles
    0.81
     Trong
    0.79
    Act Density 0.028%

    No Known Activations