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

    Neuronpedia

    INDEX
    Explanations

    Japanese words

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lack
    -0.76
    kefeller
    -0.74
     brim
    -0.74
     Bened
    -0.74
    cair
    -0.72
    phia
    -0.69
    renheit
    -0.69
     Malk
    -0.68
    angelo
    -0.67
     Grayson
    -0.66
    POSITIVE LOGITS
    aku
    0.97
    oku
    0.96
    uku
    0.91
    ushi
    0.91
    itsu
    0.90
    awa
    0.88
    etsu
    0.85
    Åį
    0.83
    ikuman
    0.81
    atsu
    0.80
    Act Density 0.103%

    No Known Activations