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

    Neuronpedia

    INDEX
    Explanations

    references to physical actions or activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.81
    ailability
    -0.68
     binding
    -0.65
    ottest
    -0.65
    dds
    -0.65
    manship
    -0.64
     context
    -0.62
    mber
    -0.62
    ortunate
    -0.62
    Submit
    -0.61
    POSITIVE LOGITS
     broom
    0.97
     miles
    0.91
     stairs
    0.89
     treadmill
    0.89
     mile
    0.88
     distances
    0.88
     kilometers
    0.86
     plank
    0.85
     err
    0.85
     kilometres
    0.82
    Act Density 0.155%

    No Known Activations