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

    Neuronpedia

    INDEX
    Explanations

    terms related to importance or priority

    oai_token-act-pair · gpt-3.5-turbo

    the word "main" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sorceress
    -0.67
    AUT
    -0.67
    omic
    -0.66
    lyak
    -0.64
     Rocks
    -0.63
    KY
    -0.62
     Scores
    -0.62
     Seconds
    -0.61
     Cunning
    -0.60
     Shards
    -0.60
    POSITIVE LOGITS
    stay
    1.13
    tenance
    0.88
    deck
    0.83
     arteries
    0.80
    main
    0.79
     main
    0.78
     gist
    0.77
     sticking
    0.77
     culprit
    0.77
     contributor
    0.76
    Act Density 0.016%

    No Known Activations