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

    Neuronpedia

    INDEX
    Explanations

    sizes and measurements, especially on a microscopic scale

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     entitlement
    -0.66
     Ready
    -0.65
     camping
    -0.65
     Saving
    -0.64
     elig
    -0.64
     AFTER
    -0.64
     withholding
    -0.64
     Healer
    -0.63
     benches
    -0.62
     Started
    -0.62
    POSITIVE LOGITS
     wavelength
    1.17
    ograms
    1.08
     nan
    1.07
     atoms
    1.04
     centimeters
    1.02
    ousand
    1.01
     diameter
    1.00
     wavelengths
    1.00
     molecules
    1.00
    imeters
    0.99
    Act Density 0.138%

    No Known Activations