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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols, specifically those related to a foreign language

    oai_token-act-pair · gpt-3.5-turbo

    question marks and indicate inquiries or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xus
    -0.94
    chnology
    -0.76
     subdu
    -0.70
     Sapphire
    -0.68
     gestation
    -0.68
     satell
    -0.68
     clipping
    -0.67
    emate
    -0.67
     deaf
    -0.66
     tremend
    -0.66
    POSITIVE LOGITS
    оÐ
    1.17
    ÑĢ
    1.13
    Ñĥ
    1.03
    о
    1.03
    enance
    0.99
    е
    0.97
    л
    0.96
    а
    0.95
    éĹ
    0.89
    į
    0.88
    Act Density 0.012%

    No Known Activations