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

    Neuronpedia

    INDEX
    Explanations

    information related to potential and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acre
    -0.17
    allon
    -0.16
    uell
    -0.15
    roadcast
    -0.15
    etwork
    -0.15
     Tie
    -0.15
    rowsable
    -0.15
    alc
    -0.14
    heit
    -0.14
    alian
    -0.14
    POSITIVE LOGITS
     unc
    0.14
     Spor
    0.14
     lowering
    0.14
     worrying
    0.14
     un
    0.13
    yst
    0.13
    eur
    0.13
    odor
    0.13
    WithName
    0.13
     Kemp
    0.13
    Act Density 0.222%

    No Known Activations