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

    Neuronpedia

    INDEX
    Explanations

    proper nouns containing the letters "kan" in sequence

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Kan" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.91
    é¾
    -0.71
    ×Ļ×
    -0.69
     FIGHT
    -0.69
    bably
    -0.66
     Aires
    -0.66
    advertisement
    -0.64
    ï¸ı
    -0.64
    inals
    -0.64
     seeker
    -0.64
    POSITIVE LOGITS
    hof
    1.00
    ji
    0.99
    ako
    0.97
    awa
    0.97
    igan
    0.93
    owa
    0.93
    itary
    0.91
    ataka
    0.90
    keye
    0.88
    atin
    0.88
    Act Density 0.019%

    No Known Activations