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

    Neuronpedia

    INDEX
    Explanations

    references to interior and exterior elements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -0.90
    nito
    -0.85
     HasFactory
    -0.82
    uxxxx
    -0.81
     Paglinawan
    -0.79
    malink
    -0.78
     Mullins
    -0.77
     Fiske
    -0.76
    ../../
    -0.74
    }")]
    -0.73
    POSITIVE LOGITS
     INTERIOR
    1.14
     Interior
    1.06
    Interior
    1.04
    nterior
    1.03
     interior
    1.02
    interior
    1.00
     interiors
    0.97
     Interiors
    0.89
    INTERIOR
    0.88
     Exterior
    0.82
    Act Density 0.002%

    No Known Activations