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

    Neuronpedia

    INDEX
    Explanations

    words related to indexes or indices, especially in the context of data or economics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific indexing terms and references related to data or economic indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lyak
    -0.81
    comings
    -0.75
     Raider
    -0.69
     Troll
    -0.69
     Rampage
    -0.68
    illet
    -0.68
     Mog
    -0.67
    Rum
    -0.67
     rave
    -0.66
    bek
    -0.66
    POSITIVE LOGITS
     index
    3.88
     indexes
    2.83
     Index
    2.80
     indices
    2.52
    index
    2.39
    Index
    2.25
     indexed
    2.12
     coefficient
    1.12
     subscript
    1.09
     appendix
    1.07
    Act Density 0.016%

    No Known Activations