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

    Neuronpedia

    INDEX
    Explanations

    words related to geographical locations, particularly names of cities or countries

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the token "ao", likely indicating a focus on a specific pattern or identifier

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå¥ij士
    -0.79
    Ö¼
    -0.69
    OFF
    -0.63
     brim
    -0.63
     itch
    -0.61
     Ster
    -0.60
     markers
    -0.60
     Hitchcock
    -0.60
    sburgh
    -0.60
     Frie
    -0.60
    POSITIVE LOGITS
    qua
    1.13
    ÄŁ
    1.11
    ao
    1.10
    zzi
    1.05
    ctor
    0.99
    ji
    0.98
    gha
    0.95
    qi
    0.94
    pport
    0.91
    uthor
    0.89
    Act Density 0.009%

    No Known Activations