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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     {
    -0.15
    verted
    -0.15
    es
    -0.15
    .Companion
    -0.15
     worth
    -0.14
    ved
    -0.14
    ing
    -0.14
    Å¡ka
    -0.14
    hed
    -0.14
    itel
    -0.13
    POSITIVE LOGITS
     Strict
    0.20
     addCriterion
    0.18
     FC
    0.17
    inject
    0.16
    use
    0.16
    observable
    0.15
    Strict
    0.15
    adal
    0.15
     Browns
    0.15
     Fragment
    0.14
    Act Density 0.018%

    No Known Activations