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

    Neuronpedia

    INDEX
    Explanations

    references to military weaponry and artillery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     knife
    -0.16
    åī£
    -0.15
     Mach
    -0.15
    erville
    -0.15
     dagger
    -0.15
     Slut
    -0.15
     Lind
    -0.15
    rive
    -0.14
     Axel
    -0.14
     пÑĢиÑĤ
    -0.14
    POSITIVE LOGITS
     battery
    0.26
     batteries
    0.26
     Battery
    0.24
     shells
    0.23
     Batter
    0.21
    Battery
    0.21
    æ¦
    0.21
     canon
    0.21
     Art
    0.20
     batter
    0.20
    Act Density 0.034%

    No Known Activations