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

    Neuronpedia

    INDEX
    Explanations

    specific locations and institutions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     besides
    -0.73
    gpu
    -0.72
     anyways
    -0.68
     resorted
    -0.68
    #$
    -0.67
     anecd
    -0.66
     Rahul
    -0.65
     suppose
    -0.64
    !!!!!
    -0.64
     automate
    -0.64
    POSITIVE LOGITS
     latter
    1.09
     same
    1.07
     Philippines
    0.99
     Netherlands
    0.97
     latest
    0.94
     National
    0.93
     aforementioned
    0.92
     largest
    0.91
     United
    0.91
     Department
    0.90
    Act Density 0.955%

    No Known Activations