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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news headlines

    oai_token-act-pair · gpt-3.5-turbo

    fragmented or incomplete sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¥µ
    -0.73
    ĭ
    -0.69
    ½
    -0.67
    ĪĴ
    -0.66
    yden
    -0.64
    nec
    -0.64
    backer
    -0.63
    cember
    -0.63
    imaru
    -0.63
    sembly
    -0.63
    POSITIVE LOGITS
    Scroll
    0.92
    Trend
    0.68
    Shape
    0.66
    ?????-
    0.65
    SHARE
    0.64
     Pict
    0.62
     Topic
    0.61
    Hum
    0.61
    ãĤ¨ãĥ«
    0.61
    natureconservancy
    0.61
    Act Density 0.184%

    No Known Activations