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

    Neuronpedia

    INDEX
    Explanations

    references to processes and documentation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avra
    -0.16
    ritt
    -0.15
    LOAT
    -0.15
    ÙĨس
    -0.15
    .glide
    -0.14
    chers
    -0.14
     Slut
    -0.14
    ZONE
    -0.14
    ombine
    -0.14
    :frame
    -0.14
    POSITIVE LOGITS
    usa
    0.16
    eny
    0.15
    ings
    0.15
    ushi
    0.14
    usi
    0.14
    alous
    0.14
     umb
    0.14
    use
    0.14
    (s
    0.14
    eter
    0.14
    Act Density 0.033%

    No Known Activations