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

    Neuronpedia

    INDEX
    Explanations

    mentions or references to expert individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to experts and expert opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [|
    -0.70
    strip
    -0.68
     Agric
    -0.68
    boats
    -0.67
    fw
    -0.66
     Shades
    -0.66
    Lago
    -0.64
    VILLE
    -0.62
     Skydragon
    -0.62
    apo
    -0.61
    POSITIVE LOGITS
    sonian
    0.97
    ulously
    0.96
     consulted
    0.93
    inent
    0.80
     interpre
    0.79
    minded
    0.77
     opinion
    0.76
     advise
    0.75
    oult
    0.74
    ieth
    0.74
    Act Density 0.031%

    No Known Activations