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

    Neuronpedia

    INDEX
    Explanations

    special characters and non-English characters

    oai_token-act-pair · gpt-3.5-turbo

    specific special characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bonded
    -0.79
     hypers
    -0.73
    combe
    -0.70
    perse
    -0.69
     clutch
    -0.68
    xus
    -0.68
    wcs
    -0.67
    cules
    -0.67
     dexter
    -0.67
     soluble
    -0.65
    POSITIVE LOGITS
    ÑĮ
    1.36
    ÑĢ
    1.32
    н
    1.31
    е
    1.29
    а
    1.26
    Ñģ
    1.23
    о
    1.23
    į
    1.18
    и
    1.17
    в
    1.14
    Act Density 0.003%

    No Known Activations