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

    Neuronpedia

    INDEX
    Explanations

    references to military actions and casualties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prite
    -0.15
    nas
    -0.15
    ikal
    -0.14
    ç¡
    -0.13
    stdarg
    -0.13
    mv
    -0.13
    aks
    -0.13
     chatte
    -0.13
    outers
    -0.13
    ÎķÎļ
    -0.13
    POSITIVE LOGITS
    zet
    0.15
     Fu
    0.15
     erotische
    0.15
    uet
    0.15
    kili
    0.14
    Fu
    0.14
     Leaders
    0.14
    аÑĢÑĮ
    0.14
    ôn
    0.14
    Unified
    0.14
    Act Density 0.014%

    No Known Activations