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

    Neuronpedia

    INDEX
    Explanations

    links and references to other content

    oai_token-act-pair · gpt-3.5-turbo

    references to links or URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥª
    -0.84
    sbm
    -0.75
    ŃĶ
    -0.71
    Ĥİ
    -0.70
    ieu
    -0.70
    factor
    -0.68
    bowl
    -0.67
    slice
    -0.66
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
    ¸
    -0.65
    POSITIVE LOGITS
     websites
    0.85
    site
    0.83
    pages
    0.83
     Youtube
    0.81
     webpage
    0.80
     URL
    0.80
     www
    0.78
     articles
    0.76
     youtube
    0.75
     URLs
    0.75
    Act Density 0.177%

    No Known Activations