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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arias
    -0.22
    iae
    -0.18
    empor
    -0.17
    geries
    -0.17
    atura
    -0.14
    oria
    -0.14
    رسÛĮ
    -0.14
    ella
    -0.14
    ráv
    -0.14
    ovich
    -0.14
    POSITIVE LOGITS
    ymoon
    0.16
    ̣
    0.14
    ipar
    0.14
     Related
    0.14
     gravity
    0.13
    gypt
    0.13
    lsa
    0.13
     serg
    0.13
    ÑĢеÑĪ
    0.13
     Äijá»Ŀi
    0.13
    Act Density 0.082%

    No Known Activations