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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "run" in various contexts and variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    run as prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.54
    +#+
    -0.48
     defaultstate
    -0.40
     pagkak
    -0.39
    izer
    -0.39
    Cec
    -0.38
    cdata
    -0.37
    spheric
    -0.37
    hender
    -0.37
     attribute
    -0.37
    POSITIVE LOGITS
     run
    1.09
     Run
    1.06
    Run
    1.02
    run
    1.00
     RUN
    1.00
    RUN
    0.94
     Runs
    0.92
    Runs
    0.86
     runs
    0.83
    runs
    0.79
    Act Density 0.036%

    No Known Activations