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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically personal names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    姫
    -0.85
    pter
    -0.81
    IZE
    -0.78
     Remastered
    -0.76
    KEN
    -0.74
    AU
    -0.74
    wagen
    -0.73
    BOOK
    -0.73
    OPLE
    -0.72
    izations
    -0.70
    POSITIVE LOGITS
     Abd
    1.01
    yssey
    0.93
    uran
    0.90
    irection
    0.90
    ication
    0.89
    ali
    0.89
    entimes
    0.88
    elf
    0.83
     Dhabi
    0.82
    uel
    0.82
    Act Density 0.006%

    No Known Activations