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

    Neuronpedia

    INDEX
    Explanations

    references to guidelines and standards related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ection
    -0.14
    ãĤĩ
    -0.14
    erre
    -0.13
    oller
    -0.13
    apesh
    -0.13
     folks
    -0.13
    ango
    -0.13
    ÑĢим
    -0.13
    974
    -0.12
    noop
    -0.12
    POSITIVE LOGITS
    iman
    0.16
    zar
    0.16
     Schro
    0.15
    aukee
    0.14
    opic
    0.14
     initState
    0.14
    borg
    0.14
    elry
    0.13
    aras
    0.13
    одо
    0.13
    Act Density 0.162%

    No Known Activations