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

    Neuronpedia

    INDEX
    Explanations

    punctuation and specific formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plex
    -0.16
    cko
    -0.15
    ãģ°ãģĭãĤĬ
    -0.15
    isses
    -0.14
    ardless
    -0.14
    mant
    -0.14
    æ´ª
    -0.14
    ushi
    -0.13
     Sez
    -0.13
     æ´
    -0.13
    POSITIVE LOGITS
    ephir
    0.16
     And
    0.15
    porto
    0.14
    And
    0.14
    èĩ
    0.13
    /umd
    0.13
     prem
    0.13
     reception
    0.13
     grou
    0.13
    ¯u
    0.13
    Act Density 0.192%

    No Known Activations