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

    Neuronpedia

    INDEX
    Explanations

    action-related words and phrases involving physical movement and encounters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.71
    MS
    -0.69
    UID
    -0.68
    RF
    -0.63
    PG
    -0.62
    ict
    -0.61
     PRODUCT
    -0.60
     Ratings
    -0.60
     proprietary
    -0.60
     OPEC
    -0.60
    POSITIVE LOGITS
     distances
    1.03
     stairs
    1.00
    izont
    0.92
     hitch
    0.90
     rapp
    0.88
     destinations
    0.87
     whence
    0.87
     trave
    0.86
    Ô
    0.84
     travers
    0.84
    Act Density 0.455%

    No Known Activations