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

    Neuronpedia

    INDEX
    Explanations

    terms relating to sharpness and precision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Doria
    -0.61
    idane
    -0.60
    BagConstraints
    -0.56
     Genet
    -0.55
    olyb
    -0.54
    nommen
    -0.54
    ovan
    -0.54
    dieux
    -0.54
    otoro
    -0.53
    itse
    -0.51
    POSITIVE LOGITS
     sharp
    3.72
    sharp
    3.22
     Sharp
    3.22
    Sharp
    3.02
     SHARP
    2.89
     sharper
    2.76
     sharpness
    2.52
     sharply
    2.25
     sharpen
    2.07
    shar
    1.96
    Act Density 0.049%

    No Known Activations