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

    Neuronpedia

    INDEX
    Explanations

    references or citations in the document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    tvguidetime
    -1.24
     وتسجيلات
    -1.21
     Signalez
    -1.17
     cherchés
    -1.16
     الرياضيه
    -1.13
     незавершена
    -1.09
     للمعارف
    -1.09
    NewUrlParser
    -1.07
    CloseOperation
    -1.05
     صوتيه
    -1.05
    POSITIVE LOGITS
     
    0.42
    ramble
    0.42
     May
    0.40
     to
    0.40
    lide
    0.37
     do
    0.37
     well
    0.37
     (
    0.36
    well
    0.36
    ↵↵
    0.36
    Act Density 0.037%

    No Known Activations