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

    Neuronpedia

    INDEX
    Explanations

    Japanese names

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals, particularly in a Japanese cultural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    getic
    -0.83
     Lyme
    -0.77
    usting
    -0.69
    20439
    -0.67
    eworld
    -0.64
    theless
    -0.63
    iction
    -0.63
    edly
    -0.63
    vable
    -0.63
     Wyoming
    -0.62
    POSITIVE LOGITS
    imura
    1.30
    amoto
    1.23
    azaki
    1.22
    ikawa
    1.21
    oka
    1.19
    imoto
    1.10
    atsu
    1.09
     Yosh
    1.08
    amaru
    1.06
    ihara
    1.03
    Act Density 0.047%

    No Known Activations