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

    Neuronpedia

    INDEX
    Explanations

    details about violent incidents involving law enforcement and mistaken identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alat
    -0.14
    itto
    -0.14
    arbeit
    -0.14
    rix
    -0.14
    rum
    -0.14
    onne
    -0.13
    idot
    -0.13
    ä½³
    -0.13
    uhan
    -0.13
    uong
    -0.13
    POSITIVE LOGITS
    560
    0.15
    交
    0.15
    çĨ
    0.14
    eczy
    0.14
     Manning
    0.13
     交
    0.13
    itsu
    0.13
    æį·
    0.13
    IRT
    0.13
    minated
    0.13
    Act Density 0.140%

    No Known Activations