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

    Neuronpedia

    INDEX
    Explanations

    words related to rules or laws governing the use of a license

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ++)
    -0.45
    риан
    -0.44
    interval
    -0.43
    fø
    -0.43
     Außen
    -0.41
     吧
    -0.41
     présidenti
    -0.41
    ÊN
    -0.41
    ėmis
    -0.41
    tical
    -0.41
    POSITIVE LOGITS
     governing
    1.21
     Governing
    1.08
    Governing
    1.02
     surla
    1.00
    MLLoader
    0.99
    RectangleBorder
    0.98
    ImageContext
    0.98
    WriteBarrier
    0.96
     Roskov
    0.96
    AutoScaleMode
    0.96
    Act Density 0.000%

    No Known Activations