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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters that do not correspond to any meaningful language or pattern

    oai_token-act-pair · gpt-3.5-turbo

    Cyrillic characters or words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Joy
    -0.73
    auga
    -0.73
    terson
    -0.71
     Spur
    -0.66
    ichita
    -0.64
    higher
    -0.63
    BIL
    -0.63
    creen
    -0.62
    cence
    -0.61
    ndra
    -0.61
    POSITIVE LOGITS
    оÐ
    1.34
    и
    1.28
    Ñĥ
    1.27
    а
    1.26
    о
    1.25
    е
    1.21
    ÑĮ
    1.00
    Ñĭ
    1.00
    ×Ļ×
    0.99
    н
    0.98
    Act Density 0.018%

    No Known Activations