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

    Neuronpedia

    INDEX
    Explanations

    sections of the document that contain punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Савезне
    -1.60
    MigrationBuilder
    -1.32
     мәкал
    -1.29
     незавершена
    -1.25
     bezeichneter
    -1.24
    Diwedd
    -1.20
     Мексичка
    -1.17
     Efq
    -1.17
    ')")
    -1.17
    ergies
    -1.16
    POSITIVE LOGITS
    ,
    1.05
     ,
    0.83
    ↵↵
    0.81
    2
    0.73
    ↵
    0.73
     (
    0.71
    (
    0.71
    -
    0.71
    1
    0.70
    ;
    0.69
    Act Density 0.373%

    No Known Activations