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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols used in written language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iciel
    -0.15
    ôm
    -0.14
    inka
    -0.14
    ستÙĩ
    -0.14
    ió
    -0.14
    culus
    -0.14
    ERSIST
    -0.13
    atched
    -0.13
    глÑı
    -0.13
    zin
    -0.13
    POSITIVE LOGITS
    egin
    0.17
     Eins
    0.16
    util
    0.15
    essler
    0.15
     FileSystem
    0.15
    ods
    0.14
    ÑĮеÑĢ
    0.14
    eil
    0.14
    _FP
    0.14
    UTIL
    0.14
    Act Density 0.001%

    No Known Activations