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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "sit" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uolo
    -0.68
     neod
    -0.66
    州
    -0.66
     modo
    -0.65
    zao
    -0.62
     “
    -0.61
     duidelijk
    -0.60
     δε
    -0.60
     Kimberly
    -0.60
    cobra
    -0.59
    POSITIVE LOGITS
     sit
    1.99
     sits
    1.82
     sitting
    1.80
     Sit
    1.80
     Sitting
    1.80
    Sit
    1.79
     SIT
    1.76
    Sitting
    1.68
    sit
    1.63
    sitting
    1.62
    Act Density 0.072%

    No Known Activations