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

    Neuronpedia

    INDEX
    Explanations

    quantitative descriptors related to frequency or number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĤ£äºĽ
    -0.16
    stå
    -0.16
     Thousands
    -0.16
     Numerous
    -0.16
    .getElements
    -0.15
    mates
    -0.15
     Various
    -0.15
    åIJĦç§į
    -0.14
    activex
    -0.14
    sian
    -0.14
    POSITIVE LOGITS
    fold
    0.33
    teenth
    0.33
     different
    0.32
    -thirds
    0.31
     separate
    0.29
    -dimensional
    0.28
    eenth
    0.27
     sets
    0.25
     dozen
    0.25
    -four
    0.24
    Act Density 0.181%

    No Known Activations