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

    Neuronpedia

    INDEX
    Explanations

    quantitative expressions or mentions of numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ολ
    -0.15
     proportions
    -0.14
    981
    -0.14
     percentages
    -0.14
    zens
    -0.14
    Lists
    -0.14
    owl
    -0.14
    /***/
    -0.13
    lds
    -0.13
    Ranges
    -0.13
    POSITIVE LOGITS
     lanes
    0.18
     hairs
    0.17
     teeth
    0.17
     syll
    0.17
     shots
    0.16
    NumberOf
    0.16
     datap
    0.16
     iterations
    0.16
     hits
    0.16
     units
    0.16
    Act Density 0.373%

    No Known Activations