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

    Neuronpedia

    INDEX
    Explanations

    programming-related commands and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -1.06
    RetentionPolicy
    -0.95
     HasFactory
    -0.94
     للمعارف
    -0.90
     الرياضيه
    -0.90
    saraba
    -0.83
    UnsafeEnabled
    -0.82
     snippetHide
    -0.80
    extAlignment
    -0.80
    IntoConstraints
    -0.79
    POSITIVE LOGITS
    e
    0.52
    en
    0.50
     list
    0.45
    ne
    0.44
    basic
    0.43
     basic
    0.43
     ID
    0.42
     Cor
    0.41
     eg
    0.41
     u
    0.40
    Act Density 0.178%

    No Known Activations