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

    Neuronpedia

    INDEX
    Explanations

    variations of punctuation or formatting used in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pres
    -0.07
    ropping
    -0.07
     ########.
    -0.07
    ych
    -0.07
    roperty
    -0.06
    елÑĮзÑı
    -0.06
    inen
    -0.06
    Pres
    -0.06
    oundary
    -0.06
    ISK
    -0.06
    POSITIVE LOGITS
    ieg
    0.07
    çIJ´
    0.06
    \grid
    0.06
    .central
    0.06
     peÄį
    0.06
    ERVED
    0.06
     Economist
    0.06
    太éĥİ
    0.06
    ries
    0.06
    bjerg
    0.05
    Act Density 0.002%

    No Known Activations