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

    Neuronpedia

    INDEX
    Explanations

    complex words with multiple syllables and a unique linguistic style

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "linguistic" or its root forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ·ãĥ£
    -0.90
    éĹĺ
    -0.84
    HCR
    -0.79
    awaru
    -0.79
    ãĥ¤
    -0.77
    ãĥģ
    -0.75
    ricanes
    -0.74
    ãĥ¯ãĥ³
    -0.72
    è¦ļéĨĴ
    -0.72
    DonaldTrump
    -0.71
    POSITIVE LOGITS
     Ling
    1.31
     ling
    1.23
    ering
    0.97
    ua
    0.91
     tong
    0.83
     Yao
    0.80
    heng
    0.76
     Liu
    0.76
     noodles
    0.76
    jing
    0.74
    Act Density 0.006%

    No Known Activations