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

    Neuronpedia

    INDEX
    Explanations

    quotes or apostrophes in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achuset
    -0.21
    rokes
    -0.16
    aub
    -0.16
    assis
    -0.15
    sian
    -0.15
    istrovstvÃŃ
    -0.15
    alace
    -0.15
    uplicates
    -0.14
    .LayoutStyle
    -0.14
     urlpatterns
    -0.14
    POSITIVE LOGITS
    bole
    0.15
    ium
    0.15
    ology
    0.15
     Tit
    0.15
    een
    0.14
    .
    0.14
    _DECLARE
    0.14
    0.14
     handle
    0.14
     successfully
    0.14
    Act Density 0.077%

    No Known Activations