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

    Neuronpedia

    INDEX
    Explanations

    references to military units and their actions or equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     knife
    -0.16
    cken
    -0.16
    wing
    -0.15
    Decoration
    -0.15
    unan
    -0.15
     Slut
    -0.15
    rive
    -0.15
     dagger
    -0.14
    adel
    -0.14
    obot
    -0.14
    POSITIVE LOGITS
     battery
    0.25
     batteries
    0.24
     Battery
    0.23
    æ¦
    0.23
     Art
    0.22
     Batter
    0.22
     shells
    0.21
     canon
    0.21
     mort
    0.20
    Canon
    0.20
    Act Density 0.021%

    No Known Activations