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

    Neuronpedia

    INDEX
    Explanations

    various forms of call-to-action phrases, instructions, and promotional content

    oai_token-act-pair · gpt-3.5-turbo

    specific phrases related to instructions or calls to action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cephal
    -0.76
    anian
    -0.73
    oat
    -0.72
    oppable
    -0.72
    jri
    -0.69
    ffen
    -0.67
    etsk
    -0.67
    auga
    -0.66
    hered
    -0.65
    endez
    -0.65
    POSITIVE LOGITS
     OUR
    1.45
     INFORMATION
    1.44
     THE
    1.43
     VIDEOS
    1.43
     THESE
    1.42
     REPORT
    1.41
     YOUR
    1.41
     THEM
    1.40
     WEEK
    1.39
    BOOK
    1.39
    Act Density 0.135%

    No Known Activations