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

    Neuronpedia

    INDEX
    Explanations

    titles of books, movies, and series

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    fulness
    -0.80
    arten
    -0.77
    hips
    -0.74
    arella
    -0.72
    adata
    -0.69
     regardless
    -0.67
    lier
    -0.67
    abella
    -0.66
    fully
    -0.66
    imaru
    -0.66
    POSITIVE LOGITS
     latter
    1.04
     aforementioned
    0.92
     Ancients
    0.91
     Confederacy
    0.91
     millennium
    0.82
     proverbial
    0.82
     smallest
    0.82
     largest
    0.80
     planet
    0.80
     dreaded
    0.80
    Act Density 1.063%

    No Known Activations