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

    Neuronpedia

    INDEX
    Explanations

    引用和定义形式的语言。

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uisse
    -0.18
     constit
    -0.17
     Kirk
    -0.15
    ono
    -0.15
     constitution
    -0.15
    оÑī
    -0.15
    cname
    -0.14
    ifix
    -0.14
    ÙĪار
    -0.14
    fav
    -0.14
    POSITIVE LOGITS
    olina
    0.15
     purpose
    0.14
    endon
    0.14
    /cop
    0.14
    uci
    0.14
     provinc
    0.14
    nech
    0.13
    è£ķ
    0.13
    дон
    0.13
    rop
    0.13
    Act Density 0.010%

    No Known Activations