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

    Neuronpedia

    INDEX
    Explanations

    frequent articles and prepositions in textual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Forgotten
    -0.17
    afe
    -0.14
    Continue
    -0.14
     confidential
    -0.14
    913
    -0.14
     Kab
    -0.14
     Bett
    -0.13
     caps
    -0.13
     forgotten
    -0.13
    avern
    -0.13
    POSITIVE LOGITS
     peÅŁ
    0.17
    quia
    0.15
    ensa
    0.14
    Ïģί
    0.14
    rez
    0.14
     ç¨
    0.14
    _ioctl
    0.14
    AYOUT
    0.14
    rede
    0.14
     Minor
    0.13
    Act Density 0.001%

    No Known Activations