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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    print
    -0.38
    plt
    -0.34
    if
    -0.33
    SBATCH
    -0.32
    ----------------------------------------------------------------------------
    -0.31
    get
    -0.31
    a
    -0.30
    ================================================================
    -0.29
    create
    -0.29
    for
    -0.28
    POSITIVE LOGITS
    (
    0.23
    -
    0.19
    -*-
    0.17
    /-
    0.17
    ately
    0.16
    ////////////////////////////////////////////////////////////////////
    0.15
     amp
    0.15
    '#
    0.15
    .synthetic
    0.15
    asley
    0.15
    Act Density 0.084%

    No Known Activations