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

    Neuronpedia

    INDEX
    Explanations

    phrases related to fictional combat and weaponry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bul
    -0.17
    бом
    -0.16
     shootout
    -0.15
    èīĩ
    -0.14
    asc
    -0.14
    dik
    -0.14
     gunfire
    -0.14
    Bullet
    -0.14
    utral
    -0.14
    _buckets
    -0.14
    POSITIVE LOGITS
     sword
    0.24
    sword
    0.22
     blade
    0.20
     swords
    0.19
     weapon
    0.19
     fencing
    0.19
    blade
    0.18
     Medieval
    0.18
     hacking
    0.17
     melee
    0.17
    Act Density 0.054%

    No Known Activations