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

    Neuronpedia

    INDEX
    Explanations

    references to sources or origins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terms
    -0.16
    ramer
    -0.14
    ares
    -0.14
    (setting
    -0.13
    IMUM
    -0.13
    TM
    -0.13
    regn
    -0.13
    ekl
    -0.13
    áºł
    -0.13
    (disposing
    -0.13
    POSITIVE LOGITS
    /to
    0.29
    alto
    0.19
    /by
    0.19
     scratch
    0.19
    alien
    0.16
    scratch
    0.15
    alim
    0.15
    ians
    0.14
    å±ŀ
    0.14
     nowhere
    0.14
    Act Density 0.335%

    No Known Activations