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

    Neuronpedia

    INDEX
    Explanations

    texts that mentions ammunition and weapons

    oai_token-act-pair · gpt-3.5-turbo

    mentions of ammunition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liness
    -0.89
    aido
    -0.84
    ŃĶ
    -0.84
    lihood
    -0.83
    nee
    -0.82
    landers
    -0.76
    visible
    -0.75
    leans
    -0.73
    yan
    -0.72
    eland
    -0.70
    POSITIVE LOGITS
     ammunition
    0.98
     cartridges
    0.92
     ammo
    0.89
     bolts
    0.88
     crates
    0.86
     pellets
    0.85
     tubes
    0.84
     dumps
    0.81
     flares
    0.81
     cans
    0.80
    Act Density 0.018%

    No Known Activations