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

    Neuronpedia

    INDEX
    Explanations

    characters related to computer programming and digital operations

    oai_token-act-pair · gpt-3.5-turbo

    symbols or indicators that imply hierarchical or navigational elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teenth
    -0.93
    onial
    -0.92
    etheless
    -0.91
    erville
    -0.90
     destro
    -0.86
    iqueness
    -0.85
    enance
    -0.83
    yssey
    -0.82
    ModLoader
    -0.81
    ivia
    -0.80
    POSITIVE LOGITS
    _>
    1.31
    =>
    0.84
    .<
    0.83
     >
    0.81
     Contents
    0.71
    ++++
    0.71
    âĸĴ
    0.69
     Preferences
    0.67
    tf
    0.66
     Dangerous
    0.65
    Act Density 0.015%

    No Known Activations