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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to "Main" as it relates to locations or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lapse
    -0.77
    uc
    -0.75
    azo
    -0.70
     curl
    -0.69
     expired
    -0.68
     breath
    -0.66
     oxide
    -0.66
    ingly
    -0.66
     expire
    -0.65
     chilling
    -0.63
    POSITIVE LOGITS
     Main
    3.71
    Main
    2.26
    main
    1.89
     main
    1.66
     Secondary
    1.22
     Primary
    1.17
     Minor
    1.01
     Side
    1.00
    Primary
    0.97
     mainline
    0.94
    Act Density 0.019%

    No Known Activations