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

    Neuronpedia

    INDEX
    Explanations

    combat-related action verbs and spells

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .mvp
    -0.17
    ardash
    -0.16
    оке
    -0.14
     tá»Ń
    -0.14
    tru
    -0.14
     action
    -0.14
    monster
    -0.13
    лиÑĨ
    -0.13
     fre
    -0.13
    luet
    -0.13
    POSITIVE LOGITS
     ranged
    0.23
     Plasma
    0.22
     plasma
    0.22
     grappling
    0.21
     Hom
    0.19
     charged
    0.17
     hom
    0.17
     Acid
    0.17
     Gat
    0.17
     Gust
    0.17
    Act Density 0.098%

    No Known Activations