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

    Neuronpedia

    INDEX
    Explanations

    proper nouns followed by "MORE" which might indicate the emphasis on something specific in a document

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "MORE" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.81
    ãĤ©
    -0.78
     Columb
    -0.72
     eg
    -0.68
    ãĥ¥
    -0.66
    ãĥĨãĤ£
    -0.65
    asus
    -0.64
    ãĤ£
    -0.62
    Filename
    -0.59
    ãĤ¬
    -0.58
    POSITIVE LOGITS
     VIDEOS
    0.77
    enthal
    0.75
    enegger
    0.73
    iciary
    0.70
    uchin
    0.69
    ellen
    0.69
     Jr
    0.66
    eller
    0.65
    eat
    0.64
    PP
    0.64
    Act Density 0.019%

    No Known Activations