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

    Neuronpedia

    INDEX
    Explanations

    references to swords and weapons in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourd
    -0.17
    tes
    -0.14
    itte
    -0.14
    orsi
    -0.14
    te
    -0.14
    åĬ¨çĶŁæĪIJ
    -0.14
    usat
    -0.13
    ldre
    -0.13
    errated
    -0.13
    dat
    -0.13
    POSITIVE LOGITS
    ALSE
    0.17
     Volk
    0.14
    elho
    0.14
    oes
    0.13
    åĬŁ
    0.13
    alion
    0.13
     turnover
    0.13
     ============================================================================↵
    0.13
    blade
    0.13
     Byl
    0.13
    Act Density 0.004%

    No Known Activations