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

    Neuronpedia

    INDEX
    Explanations

    large quantities or high numbers

    oai_token-act-pair · gpt-3.5-turbo

    words expressing extreme quantities or degrees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tags
    -0.92
    units
    -0.88
    groups
    -0.88
    forums
    -0.83
    stones
    -0.82
    lees
    -0.82
    events
    -0.81
    laws
    -0.79
    Tags
    -0.77
    Ingredients
    -0.77
    POSITIVE LOGITS
     amount
    1.27
     chunk
    1.05
     assortment
    1.01
     number
    0.97
     percentage
    0.95
     handful
    0.94
     dose
    0.90
     trove
    0.90
     degree
    0.90
     array
    0.90
    Act Density 0.233%

    No Known Activations