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

    Neuronpedia

    INDEX
    Explanations

    physical activities and practices

    oai_token-act-pair · gpt-3.5-turbo

    various forms of physical or interactive activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iverse
    -0.83
    era
    -0.79
    orthy
    -0.79
    onder
    -0.79
    arta
    -0.77
    2016
    -0.76
    tier
    -0.76
    BN
    -0.75
    Versions
    -0.74
    Europe
    -0.73
    POSITIVE LOGITS
     chewing
    1.42
     brushing
    1.38
     kissing
    1.35
     bathing
    1.34
     chanting
    1.32
     dancing
    1.32
     scratching
    1.30
     hugging
    1.30
     gardening
    1.29
     swallowing
    1.29
    Act Density 0.511%

    No Known Activations