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

    Neuronpedia

    INDEX
    Explanations

    terms related to conflict and military actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sadd
    -0.17
    anel
    -0.16
     Wong
    -0.15
    strap
    -0.14
     Gal
    -0.14
    ault
    -0.14
    rott
    -0.14
    aux
    -0.14
     anymore
    -0.14
    åŃĻ
    -0.14
    POSITIVE LOGITS
    ynamo
    0.15
    iper
    0.15
    oser
    0.15
    UIS
    0.14
    ulumi
    0.14
    uchen
    0.14
    ynos
    0.14
    ÙģØ©
    0.14
    .baidu
    0.14
    inspace
    0.14
    Act Density 0.029%

    No Known Activations