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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming structure or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     is
    -1.06
     be
    -0.85
     være
    -0.81
     are
    -0.80
     být
    -0.75
     быть
    -0.74
     être
    -0.74
     jesteś
    -0.73
     Are
    -0.69
     бути
    -0.68
    POSITIVE LOGITS
     EconPapers
    0.96
    AccessorTable
    0.94
    sizeCache
    0.88
     Monfieur
    0.79
     Anſ
    0.77
     Reſ
    0.76
    setVerticalGroup
    0.75
     AttributeSet
    0.74
    mybatisplus
    0.74
     ſtate
    0.73
    Act Density 0.616%

    No Known Activations