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

    Neuronpedia

    INDEX
    Explanations

    specific characters or encoded phrases, likely related to titles or names in a non-English context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bedo
    -0.17
    adlo
    -0.16
    adla
    -0.15
    luet
    -0.14
    lok
    -0.14
    asti
    -0.14
    voy
    -0.13
    loy
    -0.13
    idon
    -0.13
     Bust
    -0.13
    POSITIVE LOGITS
    ìĹIJ
    0.17
    ìĹIJìĦľ
    0.16
    ìĿĺ
    0.16
    íķĺ
    0.15
    ìĥģ
    0.15
     ún
    0.15
    yang
    0.14
     Yang
    0.14
    ìĿ´
    0.14
     ë¶Ģ
    0.13
    Act Density 0.001%

    No Known Activations