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

    Neuronpedia

    INDEX
    Explanations

    references to scholarly articles and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rank
    -0.17
    uron
    -0.14
    elik
    -0.14
    Ä
    -0.14
    гаÑĢ
    -0.14
    lif
    -0.13
    nek
    -0.13
    -regexp
    -0.13
    \Collections
    -0.13
    orney
    -0.13
    POSITIVE LOGITS
    μεν
    0.15
    deaux
    0.15
    /ns
    0.14
    igos
    0.14
    ombre
    0.13
    ุà¹Ī
    0.13
    Hdr
    0.13
     treat
    0.13
    ients
    0.13
    ItemCount
    0.12
    Act Density 0.036%

    No Known Activations