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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sitting in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "sit" and "lie" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rays
    -0.73
    ayer
    -0.73
     Reloaded
    -0.72
     giveaways
    -0.70
    orf
    -0.70
     bleach
    -0.69
     killer
    -0.69
     annotation
    -0.68
     emoji
    -0.68
     razor
    -0.67
    POSITIVE LOGITS
     Sit
    3.30
    Sit
    2.92
    sit
    2.49
     Lie
    1.58
     Situation
    1.30
     Chin
    1.30
     Sitting
    1.28
     Sop
    1.27
    Lie
    1.26
     Pend
    1.23
    Act Density 0.057%

    No Known Activations