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

    Neuronpedia

    INDEX
    Explanations

    unrelated or miscellaneous information not coherent or having a specific theme

    oai_token-act-pair · gpt-3.5-turbo

    references to unspecified entities or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aceous
    -0.91
    co
    -0.72
    QL
    -0.71
    ces
    -0.70
    ctor
    -0.67
    ocratic
    -0.66
    ropolis
    -0.65
    athon
    -0.64
    sole
    -0.62
    ald
    -0.61
    POSITIVE LOGITS
     challeng
    1.03
     behavi
    0.92
    ecided
    0.89
    ĸļ
    0.83
    poons
    0.81
    igham
    0.81
    worldly
    0.80
    nces
    0.79
    etheless
    0.77
    wcs
    0.77
    Act Density 0.012%

    No Known Activations