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

    Neuronpedia

    INDEX
    Explanations

    the abbreviation "Ta" followed by a specific number

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Ta" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CTR
    -0.74
    20439
    -0.73
    Ö¼
    -0.66
     CRC
    -0.66
    lessly
    -0.60
     PNG
    -0.58
    sburgh
    -0.58
     Governments
    -0.58
    士
    -0.58
     OCD
    -0.58
    POSITIVE LOGITS
    Ta
    1.07
    iba
    0.99
    plin
    0.98
    vern
    0.89
    uga
    0.88
    fts
    0.82
    oshi
    0.82
    quet
    0.80
    obin
    0.80
    ft
    0.79
    Act Density 0.013%

    No Known Activations