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

    Neuronpedia

    INDEX
    Explanations

    references to philosophical concepts and literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ÑĨеÑĢков
    -0.15
    acente
    -0.15
    ìĶ
    -0.15
     Anglic
    -0.14
     ÑĨеÑĢкви
    -0.14
    íĪ¬
    -0.14
    .px
    -0.14
    illisecond
    -0.14
     Fah
    -0.14
     church
    -0.14
    POSITIVE LOGITS
     Republic
    0.26
    Republic
    0.24
     Sok
    0.23
     dialog
    0.22
     Plato
    0.21
     Soph
    0.21
     Athens
    0.20
     City
    0.20
     city
    0.20
     Cave
    0.20
    Act Density 0.019%

    No Known Activations