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

    Neuronpedia

    INDEX
    Explanations

    commands or options displayed on a screen

    oai_token-act-pair · gpt-3.5-turbo

    the presence of empty or placeholder content in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ework
    -0.79
    itational
    -0.75
    naires
    -0.70
    ngth
    -0.67
    ights
    -0.67
    rums
    -0.66
    yss
    -0.65
    arial
    -0.65
    hift
    -0.64
    emis
    -0.63
    POSITIVE LOGITS
     Thumbnails
    0.98
    Pages
    0.87
     Tweet
    0.85
     Content
    0.83
     caption
    0.82
     guiActiveUnfocused
    0.81
    Page
    0.81
     Copy
    0.80
     Reply
    0.80
     thumbnail
    0.79
    Act Density 0.112%

    No Known Activations