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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate sharpness or clarity

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    engaruhi
    -0.82
     مرئيه
    -0.78
    Mule
    -0.76
     Mank
    -0.76
    `,
    -0.73
    ękuję
    -0.73
    RegistryLite
    -0.70
    uley
    -0.70
     Mule
    -0.69
    photobucket
    -0.68
    POSITIVE LOGITS
     Sharp
    1.77
     sharp
    1.52
     SHARP
    1.49
    sharp
    1.45
    Sharp
    1.41
     sharpness
    1.29
     sharpen
    1.25
     sharper
    1.24
     Sharpe
    1.19
     sharpening
    1.16
    Act Density 0.011%

    No Known Activations