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

    Neuronpedia

    INDEX
    Explanations

    words related to swords

    oai_token-act-pair · gpt-3.5-turbo

    references to swords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.76
    eret
    -0.76
    vent
    -0.69
    dit
    -0.68
    acent
    -0.67
    Newsletter
    -0.66
    uated
    -0.66
    ostics
    -0.65
    Organ
    -0.65
    created
    -0.62
    POSITIVE LOGITS
     swords
    1.02
     sword
    1.01
    fish
    0.95
     swall
    0.93
    axe
    0.85
    lance
    0.84
    fighter
    0.84
     blade
    0.84
     blades
    0.84
    fighting
    0.84
    Act Density 0.005%

    No Known Activations