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

    Neuronpedia

    INDEX
    Explanations

    references to small details or actions that have significant implications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     محفوظة
    -0.57
    грузки
    -0.57
    setHorizontal
    -0.56
    Yer
    -0.52
     '>=
    -0.52
     Yer
    -0.51
    ậc
    -0.51
     Knud
    -0.51
     Спи
    -0.51
    }\]
    -0.50
    POSITIVE LOGITS
     мело
    0.83
     details
    0.76
     minuti
    0.72
     detail
    0.71
     Detail
    0.69
     petits
    0.68
     detaljer
    0.68
    details
    0.66
     drob
    0.66
     detalhes
    0.66
    Act Density 0.082%

    No Known Activations