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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions of firing or shooting

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "firing" in various contexts related to action or termination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Jane
    -0.74
    xx
    -0.69
    sd
    -0.68
     Proud
    -0.68
    zzo
    -0.68
    si
    -0.67
     Soph
    -0.67
    eds
    -0.66
    Stew
    -0.66
     Dreams
    -0.65
    POSITIVE LOGITS
     firing
    1.17
     Fired
    0.95
    uracy
    0.90
     exting
    0.86
     fired
    0.85
     mosqu
    0.85
     torches
    0.82
     ammunition
    0.76
     gunfire
    0.75
     salute
    0.74
    Act Density 0.005%

    No Known Activations