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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to access and permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tp
    -0.15
    anning
    -0.15
    reamble
    -0.15
     lÃłnh
    -0.15
    isky
    -0.14
    tsy
    -0.14
    akis
    -0.13
    ικÏĮ
    -0.13
    ellipsis
    -0.13
    tn
    -0.13
    POSITIVE LOGITS
    ories
    0.29
    ory
    0.28
    ORIES
    0.23
    orie
    0.22
    oire
    0.22
    Denied
    0.21
    aries
    0.20
    -den
    0.20
    orial
    0.20
    ibles
    0.20
    Act Density 0.015%

    No Known Activations