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

    Neuronpedia

    INDEX
    Explanations

    references to violent events and firearm usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orners
    -0.16
    xit
    -0.15
     bruises
    -0.14
     åĭ
    -0.14
    685
    -0.14
    arsed
    -0.14
    imension
    -0.14
    ãĥ¢ãĥ³
    -0.13
    inflate
    -0.13
    owski
    -0.13
    POSITIVE LOGITS
     fire
    0.34
     firing
    0.34
     fired
    0.31
    -fire
    0.31
    fire
    0.27
     gunfire
    0.26
     Fire
    0.25
     shots
    0.25
    _fire
    0.24
    Fire
    0.24
    Act Density 0.088%

    No Known Activations