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

    Neuronpedia

    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turbo

    proper names, specifically those of notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irlf
    -0.71
    ttp
    -0.67
    enegger
    -0.67
    rities
    -0.63
     Cavern
    -0.62
    anchester
    -0.61
    ãĥŁ
    -0.60
    natureconservancy
    -0.59
     Laos
    -0.59
     Confederation
    -0.58
    POSITIVE LOGITS
    antage
    0.72
    owitz
    0.70
    angelo
    0.64
     Skydragon
    0.64
    iel
    0.63
     Piper
    0.62
    lish
    0.61
    Render
    0.61
    emo
    0.60
    water
    0.60
    Act Density 0.131%

    No Known Activations