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

    Neuronpedia

    INDEX
    Explanations

    references to classical literature and its themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ÄĮer
    -0.16
    ä¸įå®ī
    -0.15
    edik
    -0.14
     सन
    -0.14
    anium
    -0.14
     seins
    -0.14
    alfa
    -0.14
    ysz
    -0.13
     Saints
    -0.13
    egral
    -0.13
    POSITIVE LOGITS
     Troy
    0.37
     Od
    0.35
     Trojan
    0.34
     Hector
    0.31
     Homer
    0.31
     Hom
    0.30
    Od
    0.30
     Odyssey
    0.29
    Tro
    0.29
     Tro
    0.28
    Act Density 0.029%

    No Known Activations