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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something is more significant or complex than initially believed

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "more than just" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.71
     Coun
    -0.71
    Vers
    -0.68
     Avalon
    -0.68
     Huck
    -0.68
    dal
    -0.66
     Unch
    -0.64
    bilt
    -0.62
     Vik
    -0.62
    lane
    -0.61
    POSITIVE LOGITS
     decoration
    0.78
     clutter
    0.73
    organic
    0.68
     cosmetic
    0.66
    fix
    0.66
    isse
    0.66
     outward
    0.65
    ourning
    0.63
    owski
    0.63
    ipal
    0.63
    Act Density 0.056%

    No Known Activations