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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "sit" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uolo
    -0.80
    ⋙
    -0.70
     Valerio
    -0.67
     modo
    -0.67
     Kimberly
    -0.65
     neod
    -0.64
     Kura
    -0.64
    uey
    -0.63
     Tracey
    -0.63
    hql
    -0.62
    POSITIVE LOGITS
     sit
    1.67
     Sit
    1.60
    Sit
    1.57
     SIT
    1.53
     Sitting
    1.50
     sitting
    1.48
     sits
    1.48
    Sitting
    1.39
    SIT
    1.37
    sit
    1.34
    Act Density 0.056%

    No Known Activations