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

    Neuronpedia

    INDEX
    Explanations

    references to the location "Kan" followed by a single digit

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Kan" and its variations, indicating a focus on references to a specific place or entity associated with that term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.89
     Aires
    -0.71
    é¾
    -0.66
    suit
    -0.64
     Thumbnails
    -0.64
    dinand
    -0.63
     FIGHT
    -0.61
    ï¸ı
    -0.60
    bably
    -0.60
    inately
    -0.60
    POSITIVE LOGITS
    ji
    1.06
    hof
    1.04
    igan
    0.99
    ataka
    0.93
    igans
    0.92
    awa
    0.91
    ako
    0.90
    aho
    0.88
    ju
    0.88
    thal
    0.86
    Act Density 0.027%

    No Known Activations