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

    Neuronpedia

    INDEX
    Explanations

    examples or illustrations in the form of "e.g." or "i.e."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     мәкал
    -0.79
    osoba
    -0.78
    Salva
    -0.77
    transQ
    -0.73
     dAtA
    -0.73
    gown
    -0.73
     nakalista
    -0.72
     &'
    -0.70
     plak
    -0.69
    CloseOperation
    -0.68
    POSITIVE LOGITS
     = 
    1.04
     eg
    0.86
    verwijspagina
    0.82
    eg
    0.77
     Eg
    0.75
    BuilderFactory
    0.68
     Finlay
    0.68
    ie
    0.67
     SEGU
    0.66
    Kele
    0.65
    Act Density 0.006%

    No Known Activations