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

    Neuronpedia

    INDEX
    Explanations

    the neuron is looking for words related to size or quantity, with a focus on items that are large or powerful

    oai_token-act-pair · gpt-3.5-turbo

    the presence of various Pokémon species descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undrum
    -0.79
    elf
    -0.77
    ologue
    -0.76
    mma
    -0.68
    iom
    -0.68
    ISON
    -0.66
    ridor
    -0.64
    forcer
    -0.62
     Guide
    -0.61
    oute
    -0.61
    POSITIVE LOGITS
     amounts
    1.82
     quantities
    1.82
     chunks
    1.50
     doses
    1.45
     sums
    1.40
     portions
    1.33
     volumes
    1.30
     batches
    1.28
     percentages
    1.27
     periods
    1.27
    Act Density 0.210%

    No Known Activations