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

    Neuronpedia

    INDEX
    Explanations

    statistical terms and expressions related to mathematical guarantees and conditions within functions or models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     acostumb
    -0.34
     publicação
    -0.32
     ganado
    -0.30
     caído
    -0.29
     colectiva
    -0.28
     concentrado
    -0.28
    so
    -0.27
     gustaba
    -0.26
     بگیرید
    -0.26
     Zusammen
    -0.26
    POSITIVE LOGITS
    DockStyle
    0.86
     autorytatywna
    0.79
     Taktlose
    0.78
     Италијани
    0.75
     مرئيه
    0.74
    SharedDtor
    0.74
     Signalez
    0.73
    tagHelperRunner
    0.73
     ویکی‌پدی
    0.69
     Exactos
    0.69
    Act Density 2.133%

    No Known Activations