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

    Neuronpedia

    INDEX
    Explanations

    mentions of explosive devices like grenades

    oai_token-act-pair · gpt-3.5-turbo

    references to grenades and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tt
    -0.73
    Sea
    -0.72
    Madison
    -0.71
    oney
    -0.69
    Penn
    -0.67
    yll
    -0.65
    tem
    -0.65
    Sax
    -0.64
    morning
    -0.63
    eff
    -0.63
    POSITIVE LOGITS
     grenade
    1.32
     grenades
    1.29
     launcher
    1.09
    adier
    1.00
     Launcher
    0.97
     Grenade
    0.97
     launchers
    0.94
     detonated
    0.94
     flares
    0.91
     darts
    0.87
    Act Density 0.009%

    No Known Activations