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

    Neuronpedia

    INDEX
    Explanations

    topics related to health and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urdy
    -0.15
    embro
    -0.15
    ØŃÙĦ
    -0.14
    isson
    -0.14
    ritz
    -0.14
    UDA
    -0.14
    dto
    -0.14
    ανδ
    -0.14
    ouro
    -0.13
    andom
    -0.13
    POSITIVE LOGITS
     Uncategorized
    0.17
     Spar
    0.17
    éĽ
    0.15
    lify
    0.15
    kem
    0.14
     intimid
    0.14
    flatten
    0.13
    atest
    0.13
    /documentation
    0.13
    -alist
    0.13
    Act Density 0.008%

    No Known Activations