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

    Neuronpedia

    INDEX
    Explanations

    references to literature and notable literary works and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.55
    ון
    -0.46
    祖
    -0.42
     ?
    -0.41
    ówki
    -0.40
    穴
    -0.40
    /***/
    -0.40
    szak
    -0.40
    sikan
    -0.39
      
    -0.39
    POSITIVE LOGITS
     novels
    1.26
     fiction
    1.11
     novelist
    1.08
     literary
    1.07
     novelists
    1.06
     novel
    1.02
    novel
    1.01
     poet
    1.00
     poets
    0.99
     Novels
    0.99
    Act Density 0.318%

    No Known Activations