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

    Neuronpedia

    INDEX
    Explanations

    elements related to scientific measurements and analytical results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hypotheses
    -0.15
     بط
    -0.15
    union
    -0.15
     nou
    -0.14
     pak
    -0.14
    aden
    -0.14
     Floyd
    -0.14
    lags
    -0.14
    quot
    -0.13
    лади
    -0.13
    POSITIVE LOGITS
     qual
    0.21
     Rash
    0.19
     disorder
    0.18
     Mattis
    0.18
     frustration
    0.18
     bulk
    0.18
     electronic
    0.17
     excit
    0.17
     Disorder
    0.17
     tunnel
    0.17
    Act Density 0.103%

    No Known Activations