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

    Neuronpedia

    INDEX
    Explanations

    complex questions or discussions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "question."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emetery
    -0.91
    rites
    -0.87
    azeera
    -0.82
    ufact
    -0.79
     limbs
    -0.73
    ccording
    -0.72
    lim
    -0.72
    alty
    -0.71
    luaj
    -0.70
    é¾
    -0.70
    POSITIVE LOGITS
    naires
    1.58
    naire
    1.32
     question
    1.09
     questions
    0.93
     Questions
    0.85
    question
    0.81
     unanswered
    0.80
    phrase
    0.77
     Question
    0.73
     moot
    0.72
    Act Density 0.023%

    No Known Activations