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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the existence or non-existence of conditions and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fous
    -0.51
     rând
    -0.50
     corso
    -0.47
     set
    -0.46
    akar
    -0.45
    دو
    -0.45
    skel
    -0.44
     bäst
    -0.44
    єр
    -0.43
     sete
    -0.43
    POSITIVE LOGITS
     estekak
    0.91
     Meksiku
    0.87
    tvguidetime
    0.84
     الوطنيه
    0.80
    GraphicsUnit
    0.75
    principalTable
    0.75
    цезда
    0.73
    TypedDataSet
    0.72
    roslav
    0.71
    nexpected
    0.71
    Act Density 0.333%

    No Known Activations