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

    Neuronpedia

    INDEX
    Explanations

    Roman numerals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.17
    ãģŁãĤĬ
    -0.16
    nie
    -0.15
    άλ
    -0.15
    orre
    -0.15
    NDAR
    -0.15
    OfType
    -0.15
    ulen
    -0.15
    sik
    -0.15
    ned
    -0.15
    POSITIVE LOGITS
    407
    0.15
    ouv
    0.15
    inois
    0.15
    wash
    0.15
    907
    0.15
    IX
    0.14
     Wed
    0.14
    306
    0.14
    ray
    0.14
    ernes
    0.14
    Act Density 0.038%

    No Known Activations