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

    Neuronpedia

    INDEX
    Explanations

    numerals and technical symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols, particularly the character "¸"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.81
    rants
    -0.75
    nings
    -0.73
    eatures
    -0.73
     Flavoring
    -0.71
    ancies
    -0.70
    icals
    -0.70
    zona
    -0.69
     synerg
    -0.67
    detail
    -0.67
    POSITIVE LOGITS
    ãĤ§
    1.10
    ãĥ£
    0.99
    Ö¼
    0.94
    ãĥ¥
    0.92
    256
    0.89
    ¸
    0.88
    Ö
    0.86
    wark
    0.83
    ¾
    0.82
    Ì
    0.81
    Act Density 0.011%

    No Known Activations