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

    Neuronpedia

    INDEX
    Explanations

    commands or requests to cease an action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.67
    tvguidetime
    -0.62
    Charsets
    -0.61
    beqa
    -0.60
     урна
    -0.59
    hydrates
    -0.59
     Huxley
    -0.57
     الحره
    -0.55
     indisponible
    -0.55
    butuhkan
    -0.54
    POSITIVE LOGITS
     stop
    3.81
     stops
    3.59
     Stop
    3.52
     stopped
    3.38
    stop
    3.32
    Stop
    3.29
     Stops
    3.25
     STOP
    3.24
     stopping
    3.15
    stops
    3.08
    Act Density 0.072%

    No Known Activations