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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "sit" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.71
    numerusform
    -0.64
    ⋙
    -0.63
     AssemblyProduct
    -0.60
    RTDA
    -0.59
    uolo
    -0.54
    Continua
    -0.54
    klere
    -0.53
    +++++
    -0.52
    ümmer
    -0.52
    POSITIVE LOGITS
     Sit
    0.96
    Sit
    0.96
     sit
    0.95
    sit
    0.82
    SIT
    0.80
     sits
    0.78
     sitzen
    0.78
     SIT
    0.76
    坐
    0.73
     sitting
    0.70
    Act Density 0.061%

    No Known Activations