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

    Neuronpedia

    INDEX
    Explanations

    German characters with diacritics

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ividual
    -0.73
     Luther
    -0.68
     Strongh
    -0.67
    ertodd
    -0.66
     Cobra
    -0.66
     Eaton
    -0.66
    ovember
    -0.65
     Vaugh
    -0.65
     Ashton
    -0.64
    oreal
    -0.64
    POSITIVE LOGITS
    1.11
    ·
    1.08
    ¸
    1.05
    ¿
    1.04
    ĸ
    0.99
    ü
    0.97
    ³
    0.95
    eh
    0.93
    ĺ
    0.92
    ½
    0.90
    Act Density 0.015%

    No Known Activations