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

    Neuronpedia

    INDEX
    Explanations

    words indicating simplification or disregard in processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Escolar
    -0.52
     scolaires
    -0.51
     secondaire
    -0.47
    segno
    -0.46
     évaluation
    -0.46
     scolaire
    -0.46
     lauk
    -0.45
    brot
    -0.44
     decorativa
    -0.43
    eval
    -0.43
    POSITIVE LOGITS
    SequentialGroup
    0.93
    AutoScaleMode
    0.90
     للمعارف
    0.87
    principalColumn
    0.86
    AddTagHelper
    0.86
     EconPapers
    0.86
     defaultstate
    0.83
    principalTable
    0.82
    DockStyle
    0.78
    存于互联网档案馆
    0.76
    Act Density 0.356%

    No Known Activations