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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sizes and dimensions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of size in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mit
    -0.68
     aura
    -0.64
     predecessor
    -0.61
    glas
    -0.61
     property
    -0.60
    chard
    -0.58
     Committee
    -0.58
    andum
    -0.58
    alyst
    -0.58
     catalyst
    -0.57
    POSITIVE LOGITS
     sizes
    3.57
     lengths
    1.80
     sizing
    1.70
     shapes
    1.55
     formats
    1.51
     heights
    1.42
     styles
    1.41
     size
    1.41
     configurations
    1.39
     weights
    1.36
    Act Density 0.014%

    No Known Activations