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

    Neuronpedia

    INDEX
    Explanations

    adjectives and measurements related to size

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications related to measurements of products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surroundings
    -0.71
     Sund
    -0.71
     newcomers
    -0.69
     averages
    -0.69
     Annotations
    -0.68
     Nasa
    -0.67
     merits
    -0.67
     ruins
    -0.66
     poets
    -0.66
     commencement
    -0.66
    POSITIVE LOGITS
    inch
    1.64
    digit
    1.43
    liter
    1.36
    degree
    1.36
    slot
    1.34
    layer
    1.33
    pound
    1.32
    sided
    1.32
    meg
    1.31
    volt
    1.29
    Act Density 0.051%

    No Known Activations