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

    Neuronpedia

    INDEX
    Explanations

    phrases prompting the reader to check out something

    oai_token-act-pair · gpt-3.5-turbo

    calls to action encouraging the reader to check out content or links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suscept
    -0.83
     reluct
    -0.68
    lishes
    -0.65
     mathemat
    -0.63
     inval
    -0.62
    cffffcc
    -0.61
    onte
    -0.59
    EStreamFrame
    -0.59
    OF
    -0.59
    ody
    -0.58
    POSITIVE LOGITS
    mate
    1.27
    lists
    1.01
     out
    1.00
    boxes
    0.97
    list
    0.92
    out
    0.92
    points
    0.87
    mates
    0.87
    outs
    0.85
    point
    0.78
    Act Density 0.017%

    No Known Activations