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

    Neuronpedia

    INDEX
    Explanations

    references to proximity or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to comparisons and rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Synopsis
    -0.65
     photographs
    -0.65
     evid
    -0.64
     documents
    -0.64
    gered
    -0.63
    Published
    -0.62
    products
    -0.61
     firsthand
    -0.61
     unfolds
    -0.61
    igraph
    -0.61
    POSITIVE LOGITS
     mediocre
    1.04
     parity
    0.99
     +/-
    0.96
    -.
    0.92
     borderline
    0.91
     obscurity
    0.90
     0
    0.89
     percentile
    0.89
     Lv
    0.86
     respectable
    0.85
    Act Density 0.404%

    No Known Activations