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

    Neuronpedia

    INDEX
    Explanations

    words related to sharpness, intensity, and contrasts

    oai_token-act-pair · gpt-3.5-turbo

    references to sharpness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alive
    -0.83
    FORE
    -0.75
    uthor
    -0.71
    YL
    -0.71
    pty
    -0.70
     Million
    -0.68
    ORED
    -0.68
    perty
    -0.68
    akeru
    -0.66
     Incarnation
    -0.65
    POSITIVE LOGITS
    ened
    1.48
    ening
    1.46
    est
    1.18
    ener
    1.11
    ness
    1.03
    eners
    1.00
     edges
    0.99
    eness
    0.90
     contrasts
    0.86
    itudinal
    0.86
    Act Density 0.035%

    No Known Activations