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

    Neuronpedia

    INDEX
    Explanations

    numerical comparisons such as "most," "few," and "only" followed by a descriptor

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize comparisons or rankings among entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fulness
    -0.75
    lean
    -0.73
    iture
    -0.71
     Akin
    -0.66
    livion
    -0.65
    let
    -0.65
    each
    -0.63
    CLE
    -0.63
    BW
    -0.62
    ago
    -0.62
    POSITIVE LOGITS
     busiest
    1.01
     earliest
    0.94
     strongest
    0.93
     hottest
    0.89
     proverbial
    0.89
     fastest
    0.88
     highest
    0.88
     largest
    0.87
     finest
    0.82
     richest
    0.82
    Act Density 0.094%

    No Known Activations