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

    Neuronpedia

    INDEX
    Explanations

    parentheses and their associated structure in code

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.72
    dafx
    -0.65
     réguli
    -0.65
    клопе
    -0.63
    AccessorTable
    -0.63
    EMPL
    -0.63
    RenderAtEndOf
    -0.61
     umano
    -0.60
     normalidad
    -0.57
     méda
    -0.57
    POSITIVE LOGITS
     OFDb
    0.65
    StartPosition
    0.56
    ニーカー
    0.56
    ItemBackground
    0.56
     rum
    0.53
    ete
    0.52
     Rum
    0.52
     fous
    0.51
    iastes
    0.50
     FMI
    0.49
    Act Density 0.005%

    No Known Activations