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

    Neuronpedia

    INDEX
    Explanations

    references to various leagues and organizational affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achi
    -0.17
    opsis
    -0.17
    angi
    -0.16
     Ingen
    -0.15
    elson
    -0.15
    ikki
    -0.15
    cola
    -0.15
     conce
    -0.15
     laid
    -0.14
    üns
    -0.14
    POSITIVE LOGITS
    enci
    0.17
    alet
    0.15
    lore
    0.15
    undry
    0.15
    oric
    0.14
    ozilla
    0.14
    uida
    0.14
    edla
    0.14
    oteric
    0.14
    .scalablytyped
    0.14
    Act Density 0.012%

    No Known Activations