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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures and significant moments in classical literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÐĽÐŀ
    -0.17
     Royal
    -0.15
     roc
    -0.15
    erdale
    -0.14
     Castle
    -0.14
    æ¡IJ
    -0.14
    (exports
    -0.14
     Majesty
    -0.14
    lette
    -0.14
    ẫn
    -0.14
    POSITIVE LOGITS
     consul
    0.24
    gens
    0.23
     Caesar
    0.21
     Campus
    0.19
     Marcus
    0.18
     Senate
    0.18
     Pra
    0.18
     senator
    0.18
     Tribune
    0.18
     pra
    0.18
    Act Density 0.018%

    No Known Activations