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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceptions or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elu
    -0.15
    ward
    -0.14
    esson
    -0.14
     Hö
    -0.14
    inant
    -0.14
    plen
    -0.14
    unker
    -0.14
    hee
    -0.13
    idis
    -0.13
    аÑĢод
    -0.13
    POSITIVE LOGITS
    üzel
    0.15
    -global
    0.14
    ween
    0.14
    -tm
    0.14
    UTTON
    0.14
    iÄįky
    0.13
     chick
    0.13
    à¤ĸ
    0.13
    ض
    0.13
    raphics
    0.13
    Act Density 0.021%

    No Known Activations