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

    Neuronpedia

    INDEX
    Explanations

    references to classic movies and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ัมà¸ŀ
    -0.15
    987
    -0.15
    iswa
    -0.14
    roid
    -0.14
    raud
    -0.14
     hạ
    -0.14
    lied
    -0.14
    385
    -0.14
    ->
    -0.14
    980
    -0.14
    POSITIVE LOGITS
     Byrne
    0.15
    øj
    0.14
    andan
    0.14
    OMEM
    0.14
    utex
    0.14
    .Deserialize
    0.14
     Gregory
    0.13
     Grimm
    0.13
    _PATCH
    0.13
    LOGGER
    0.13
    Act Density 0.014%

    No Known Activations