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

    Neuronpedia

    INDEX
    Explanations

    descriptive attributes of size and weight

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ***!
    -0.60
    ########.
    -0.59
     myſelf
    -0.58
     raso
    -0.57
     fhew
    -0.57
    ADELPHIA
    -0.57
    :✨
    -0.56
    Autoritní
    -0.56
     وتسجيلات
    -0.53
     Vierge
    -0.52
    POSITIVE LOGITS
     size
    0.73
     Size
    0.64
    Size
    0.59
     footprint
    0.58
    笨
    0.58
     endfor
    0.58
    getDescriptor
    0.57
     enlarged
    0.57
    Bigger
    0.57
    size
    0.56
    Act Density 0.126%

    No Known Activations