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

    Neuronpedia

    INDEX
    Explanations

    parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uman
    -0.16
    ãĥ¼ãĥŀ
    -0.14
    веÑĤ
    -0.14
    INVAL
    -0.14
    opoly
    -0.14
     Tweets
    -0.13
     integrity
    -0.13
    åĪ¥
    -0.13
    it
    -0.13
    icast
    -0.13
    POSITIVE LOGITS
    .ISupportInitialize
    0.18
    ornings
    0.17
    hetto
    0.16
    ANTE
    0.16
    AP
    0.14
    usat
    0.14
    ulkan
    0.14
    avian
    0.14
    BarItem
    0.14
    ĺ认
    0.14
    Act Density 0.007%

    No Known Activations