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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to health and well-being

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to health, wellness, and efficiency improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.75
    ortium
    -0.72
    arro
    -0.66
    ritten
    -0.63
    ä¸ī
    -0.62
     surn
    -0.59
    vernment
    -0.59
     Catal
    -0.59
     âĢİ
    -0.57
    numbered
    -0.55
    POSITIVE LOGITS
     undesirable
    0.78
     unwanted
    0.76
     undes
    0.75
     conserve
    0.73
     manageable
    0.72
     wearer
    0.72
     minimize
    0.71
     congest
    0.70
     moisture
    0.70
     efficiently
    0.70
    Act Density 0.908%

    No Known Activations