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

    Neuronpedia

    INDEX
    Explanations

    adjectives and descriptions related to size, scale, and extremes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     kram
    -0.66
     silang
    -0.64
     permu
    -0.64
     asfal
    -0.59
     raso
    -0.59
     ilang
    -0.58
     perif
    -0.57
     sarili
    -0.56
     dita
    -0.56
     kras
    -0.55
    POSITIVE LOGITS
     size
    1.04
     bigger
    0.96
     larger
    0.96
     sizes
    0.94
    size
    0.94
     Size
    0.92
    Size
    0.90
    Bigger
    0.89
     sized
    0.89
     Larger
    0.86
    Act Density 0.779%

    No Known Activations