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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceptions or additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IRTUAL
    -0.16
    abras
    -0.15
    ibr
    -0.14
    Įĵ
    -0.14
    çªģ
    -0.14
     Sphinx
    -0.14
    èİİ
    -0.14
    insky
    -0.14
     Wed
    -0.13
     Westbrook
    -0.13
    POSITIVE LOGITS
    ekk
    0.15
    azen
    0.15
    orado
    0.15
    olan
    0.14
    oval
    0.14
     smo
    0.14
    .Metadata
    0.14
    iliÄŁi
    0.14
    icts
    0.14
     Chuck
    0.14
    Act Density 0.018%

    No Known Activations