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

    Neuronpedia

    INDEX
    Explanations

    statistics or numerical figures mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to percentages and growth rates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lows
    -0.69
     organs
    -0.67
     machines
    -0.66
     devils
    -0.66
     Machines
    -0.66
     IDs
    -0.66
     fluids
    -0.65
     guts
    -0.65
     secrets
    -0.64
     embassies
    -0.64
    POSITIVE LOGITS
    %-
    1.14
     kilomet
    0.94
     percent
    0.94
     mile
    0.92
    th
    0.91
    %
    0.91
    -
    0.89
    fold
    0.89
     metre
    0.89
    mile
    0.88
    Act Density 0.114%

    No Known Activations