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

    Neuronpedia

    INDEX
    Explanations

    questions in text

    oai_token-act-pair · gpt-3.5-turbo

    references to questions and answers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.78
    orpor
    -0.77
    ected
    -0.76
    rites
    -0.75
    agically
    -0.71
    oiler
    -0.66
    axy
    -0.60
     Tycoon
    -0.59
    ont
    -0.59
     emulate
    -0.58
    POSITIVE LOGITS
    naires
    1.59
    naire
    1.44
     answered
    1.24
     answ
    1.13
    Answer
    1.11
    answer
    1.08
     asked
    1.07
    answered
    1.07
     posed
    1.07
     questions
    0.97
    Act Density 0.064%

    No Known Activations