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

    Neuronpedia

    INDEX
    Explanations

    references to test-related content or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fil
    -0.15
     null
    -0.15
     Hind
    -0.15
    gie
    -0.14
     dem
    -0.14
     carbon
    -0.14
     perception
    -0.14
     dull
    -0.14
    stats
    -0.14
     diss
    -0.14
    POSITIVE LOGITS
    ÙİÙĪ
    0.17
    ANGO
    0.17
    ouro
    0.17
    .jupiter
    0.15
     Yön
    0.14
    pto
    0.14
    LEAN
    0.14
    kinson
    0.14
    IDEO
    0.14
    idot
    0.14
    Act Density 0.040%

    No Known Activations