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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and verbs in the third person

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    area
    -0.72
    past
    -0.68
    mpire
    -0.66
    fleet
    -0.66
    aye
    -0.65
    lator
    -0.65
    itaire
    -0.64
    angular
    -0.62
     Minute
    -0.62
    picture
    -0.62
    POSITIVE LOGITS
    zbollah
    0.78
     redes
    0.74
     rul
    0.71
     experien
    0.71
     fools
    0.65
     releases
    0.65
     succeeds
    0.64
     detractors
    0.64
     succeeded
    0.63
     puzzled
    0.62
    Act Density 0.441%

    No Known Activations