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

    Neuronpedia

    INDEX
    Explanations

    statements that express assumptions or conclusions in a mathematical or formal context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.66
    addCriterion
    -0.62
    WriteAttribute
    -0.56
    Історія
    -0.54
    elfs
    -0.53
    GUILayout
    -0.53
     puntata
    -0.52
     begleitet
    -0.52
    łasz
    -0.51
    !*\
    -0.51
    POSITIVE LOGITS
    modb
    0.64
    MLLoader
    0.56
    PyExc
    0.54
    rawDesc
    0.53
     Possibly
    0.50
    #+#
    0.49
    Catégorie
    0.49
    Possibly
    0.48
     possibly
    0.47
    tigt
    0.47
    Act Density 0.069%

    No Known Activations