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

    Neuronpedia

    INDEX
    Explanations

    references to the start or introduction of content in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dre
    -0.17
    YY
    -0.15
    ane
    -0.15
    ANE
    -0.14
     Trem
    -0.14
     Ùħض
    -0.14
    fov
    -0.14
    enes
    -0.14
    ensch
    -0.14
    skin
    -0.14
    POSITIVE LOGITS
    635
    0.15
    uren
    0.14
    å¼ı
    0.14
    itched
    0.14
    orte
    0.14
    werp
    0.14
    core
    0.14
    ogn
    0.13
     NSLayoutConstraint
    0.13
    bor
    0.13
    Act Density 0.023%

    No Known Activations