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

    Neuronpedia

    INDEX
    Explanations

    references to sharpness or related qualities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sharp, sharper, sharpness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    />";
    -0.51
    ########.
    -0.51
    LLocation
    -0.49
    isEnd
    -0.49
     Vessel
    -0.47
     Omnibus
    -0.46
    exitRule
    -0.46
    Royce
    -0.45
     Royce
    -0.44
     Dons
    -0.44
    POSITIVE LOGITS
     Sharp
    1.40
     SHARP
    1.34
    Sharp
    1.27
    sharp
    1.27
     sharp
    1.24
     sharpen
    1.19
     sharpness
    1.16
     Sharpe
    1.13
     sharpening
    1.09
     sharper
    1.06
    Act Density 0.005%

    No Known Activations