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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or numerical relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    declspec
    -0.16
    ANE
    -0.15
    dan
    -0.15
    xac
    -0.14
     McCl
    -0.14
     Ty
    -0.14
    iran
    -0.13
     vice
    -0.13
    ứ
    -0.13
     Ortiz
    -0.13
    POSITIVE LOGITS
    853
    0.16
    ecut
    0.15
    fragistics
    0.15
    rollo
    0.15
    nings
    0.15
    нож
    0.15
    egend
    0.14
    adt
    0.14
    ÑĨеÑĢ
    0.13
    Looper
    0.13
    Act Density 0.015%

    No Known Activations