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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers and variable names commonly used in programming or data handling contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idual
    -0.27
    ocab
    -0.26
    rength
    -0.25
    parison
    -0.25
    ighbor
    -0.25
    c
    -0.24
    ernel
    -0.24
    p
    -0.24
    d
    -0.24
    ilarity
    -0.24
    POSITIVE LOGITS
    auc
    0.18
    eah
    0.18
    aq
    0.16
    jvu
    0.16
    eria
    0.16
    erne
    0.15
    ibraries
    0.15
    adioButton
    0.15
    sWith
    0.15
    itulo
    0.15
    Act Density 0.041%

    No Known Activations