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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pry
    -0.15
    egg
    -0.14
     оно
    -0.14
    tha
    -0.13
    jec
    -0.13
    kos
    -0.13
    Ñĥка
    -0.13
     terr
    -0.13
     Perr
    -0.13
    iminal
    -0.13
    POSITIVE LOGITS
    enheim
    0.15
    Å¡ak
    0.15
    owler
    0.14
    .weixin
    0.14
    rix
    0.14
     ÙħعÙĦ
    0.14
    (er
    0.14
     easier
    0.14
    ADX
    0.14
    ÅĻej
    0.14
    Act Density 0.283%

    No Known Activations