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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to Japanese locations and figures

    oai_token-act-pair · gpt-3.5-turbo

    names of people and places, particularly in relation to Japanese culture and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sheet
    -0.84
     Lyme
    -0.71
    osc
    -0.71
    rot
    -0.70
    lov
    -0.67
    sheets
    -0.66
    brook
    -0.64
     troopers
    -0.62
    bg
    -0.62
    sylv
    -0.62
    POSITIVE LOGITS
    amoto
    1.22
    atsu
    1.19
    azaki
    1.14
    itsu
    1.12
    ichi
    1.05
    ya
    1.04
     Shogun
    1.04
    ushima
    1.03
     Yosh
    1.02
    oka
    1.00
    Act Density 0.030%

    No Known Activations