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

    Neuronpedia

    INDEX
    Explanations

    instances of dashes or interruptions in text, indicating shifts in thought or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vard
    -0.58
     υπό
    -0.56
    bufio
    -0.55
    انيف
    -0.53
    flan
    -0.51
    ONIA
    -0.51
    IUrlHelper
    -0.51
    SHEET
    -0.50
    ẫu
    -0.50
     Thus
    -0.49
    POSITIVE LOGITS
     EconPapers
    0.79
    DialogContent
    0.73
     disambiguazione
    0.67
    makeConstraints
    0.66
    saraba
    0.64
     marito
    0.63
     المعيارى
    0.62
    رشف
    0.62
    ViewFeatures
    0.61
     magique
    0.57
    Act Density 0.119%

    No Known Activations