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

    Neuronpedia

    INDEX
    Explanations

    references to film titles and production details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auga
    -0.17
    edback
    -0.17
    ecko
    -0.17
    aney
    -0.16
    efon
    -0.15
    ÑĢедиÑĤ
    -0.15
    awah
    -0.15
    .scalablytyped
    -0.15
    _FN
    -0.15
    anza
    -0.14
    POSITIVE LOGITS
    film
    0.17
     Thanh
    0.17
    acia
    0.16
     Feature
    0.16
    éĻ¢
    0.16
     FEATURES
    0.16
    ritt
    0.15
     feature
    0.15
    distributed
    0.15
     wag
    0.15
    Act Density 0.072%

    No Known Activations