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

    Neuronpedia

    INDEX
    Explanations

    references to screen or image resolutions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of image resolution in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    redo
    -0.89
    tail
    -0.79
    bara
    -0.77
     Hawth
    -0.73
     McH
    -0.72
    erd
    -0.71
    irc
    -0.71
    rium
    -0.71
    ardy
    -0.70
    epend
    -0.70
    POSITIVE LOGITS
     resolution
    1.11
     resolutions
    1.06
     Resolution
    1.05
    olution
    0.78
    resolution
    0.76
     sickness
    0.74
    velength
    0.70
     Telescope
    0.69
     sensitivity
    0.69
    Texture
    0.68
    Act Density 0.012%

    No Known Activations