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

    Neuronpedia

    INDEX
    Explanations

    references to novels and literary works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otheby
    -0.73
     Keim
    -0.70
    umplimiento
    -0.68
     InputDecoration
    -0.63
     Respect
    -0.63
    toplasm
    -0.63
    IsContent
    -0.62
    Respect
    -0.62
     respect
    -0.61
    Décès
    -0.60
    POSITIVE LOGITS
     novel
    1.50
    Novel
    1.43
    novel
    1.32
     Novel
    1.31
     NOVEL
    1.26
     novels
    1.22
     Novels
    1.13
     fiction
    1.08
     novela
    0.89
     Fiction
    0.87
    Act Density 0.171%

    No Known Activations