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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the use of excessive force

    oai_token-act-pair · gpt-3.5-turbo

    references to excessive or disproportionate behavior or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    better
    -0.81
    ector
    -0.79
    stone
    -0.78
    ect
    -0.77
    imore
    -0.73
    spot
    -0.72
    herer
    -0.72
    bard
    -0.70
    stones
    -0.69
    scene
    -0.69
    POSITIVE LOGITS
     amounts
    0.99
     reliance
    0.94
     haste
    0.89
     complexity
    0.88
     burdens
    0.87
     caution
    0.87
     consumption
    0.87
     burden
    0.86
     scrutiny
    0.82
     quantities
    0.81
    Act Density 0.061%

    No Known Activations