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

    Neuronpedia

    INDEX
    Explanations

    terms related to large scale operations or quantities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to size or scale

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulpt
    -0.83
    undrum
    -0.80
    iquette
    -0.77
     Canaver
    -0.76
     Guide
    -0.73
     Parade
    -0.72
    pty
    -0.71
    elf
    -0.71
     Statue
    -0.71
    ilogy
    -0.69
    POSITIVE LOGITS
     amounts
    1.25
     quantities
    1.21
     exposures
    1.13
     doses
    1.12
     batches
    1.09
     (>
    1.07
     periods
    1.06
     concentrations
    1.05
     levels
    0.97
     environments
    0.97
    Act Density 0.214%

    No Known Activations