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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to news or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĻ¥
    -0.62
    natureconservancy
    -0.60
    JV
    -0.57
    Streamer
    -0.56
     largeDownload
    -0.53
    ZI
    -0.51
     toile
    -0.50
    Enlarge
    -0.50
    bender
    -0.49
     mathemat
    -0.49
    POSITIVE LOGITS
     the
    1.47
     those
    1.03
     its
    1.01
     their
    0.96
     our
    0.96
     his
    0.92
     these
    0.91
     some
    0.91
     a
    0.90
     an
    0.89
    Act Density 2.120%

    No Known Activations