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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant changes or improvements in a situation or process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Gesture
    -0.17
    Guard
    -0.17
     Gesture
    -0.17
     Guardians
    -0.16
     Goldman
    -0.16
    /Graphics
    -0.16
     Gaming
    -0.16
    azed
    -0.15
    ãĥ¼ãĥĭ
    -0.15
     Gross
    -0.15
    POSITIVE LOGITS
     gear
    0.42
    -g
    0.42
     gears
    0.33
    gear
    0.30
     Gear
    0.29
     tooth
    0.28
    é½
    0.28
     Tooth
    0.28
     teeth
    0.27
    _g
    0.26
    Act Density 0.022%

    No Known Activations