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

    Neuronpedia

    INDEX
    Explanations

    references to yoga and related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to yoga and related practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hyde
    -0.78
    etary
    -0.70
    osal
    -0.69
    strous
    -0.68
    ictional
    -0.67
    vous
    -0.67
    ————————————————
    -0.66
    ilial
    -0.65
    otent
    -0.64
    ensable
    -0.63
    POSITIVE LOGITS
     yoga
    0.97
     pants
    0.90
     mats
    0.89
    oga
    0.89
     yog
    0.86
     instructor
    0.85
     meditation
    0.85
     guru
    0.83
     studio
    0.80
    pants
    0.76
    Act Density 0.012%

    No Known Activations