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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their corresponding mathematical formatting or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itan
    -0.17
    arcer
    -0.15
     Hao
    -0.14
    ildo
    -0.14
    quito
    -0.14
     zas
    -0.14
     داÙĨÙĦÙĪد
    -0.13
     assail
    -0.13
    ãĤ¸ãĥ¥
    -0.13
    .kr
    -0.13
    POSITIVE LOGITS
    åĬ¹
    0.16
    regon
    0.15
    ALSE
    0.15
    รà¸ģ
    0.15
    dek
    0.15
    hall
    0.15
     Gerr
    0.14
    ãĥ³ãĥĸ
    0.14
    ython
    0.14
    ë°©
    0.14
    Act Density 0.008%

    No Known Activations