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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation marks to indicate emphasis or directions

    oai_token-act-pair · gpt-3.5-turbo

    symbols typically associated with user interface elements like arrows or navigational prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bengal
    -0.81
    ured
    -0.71
    ozy
    -0.70
     Bucc
    -0.68
    edo
    -0.66
     Rack
    -0.65
    ous
    -0.64
     Shank
    -0.64
     dispers
    -0.63
    ãĥ¼ãĥĨ
    -0.62
    POSITIVE LOGITS
    SOURCE
    1.04
    MORE
    0.92
    HEAD
    0.87
    PER
    0.80
    LAB
    0.79
    _>
    0.78
    [[
    0.78
    wcsstore
    0.78
    lations
    0.77
    <<
    0.77
    Act Density 0.019%

    No Known Activations