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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases indicating falseness

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Hecht
    -0.77
    ToJson
    -0.73
    akesh
    -0.73
    glVertex
    -0.69
     chré
    -0.69
    زیین
    -0.69
     comunale
    -0.68
     AttributeSet
    -0.65
    EndContext
    -0.64
    chaikovsky
    -0.64
    POSITIVE LOGITS
     []:
    0.82
    GraphicsUnit
    0.78
    ation
    0.73
    ]^{-
    0.69
     Balo
    0.66
    0.66
     }^{-
    0.66
    ."—
    0.63
     McCartney
    0.63
     Hæ
    0.62
    Act Density 0.021%

    No Known Activations