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

    Neuronpedia

    INDEX
    Explanations

    references to legal cases and medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ()][
    -0.76
    tut
    -0.74
     Firestone
    -0.73
    getMinutes
    -0.73
    lwjgl
    -0.73
    ńcz
    -0.72
    LBL
    -0.71
    al
    -0.70
    vaux
    -0.70
    endregion
    -0.69
    POSITIVE LOGITS
     pomegranate
    0.84
    gasus
    0.83
     Pome
    0.81
    DrawerToggle
    0.79
    stdlib
    0.78
    jména
    0.78
     serangga
    0.77
     Fiske
    0.76
     Tarn
    0.76
     Holt
    0.76
    Act Density 2.191%

    No Known Activations