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

    Neuronpedia

    INDEX
    Explanations

    phrases related to questioning and inquiry

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to inquiries or questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.86
    minist
    -0.74
    rites
    -0.73
    emetery
    -0.73
    assad
    -0.71
    mental
    -0.71
    ONSORED
    -0.68
    yss
    -0.67
    adder
    -0.67
    rush
    -0.66
    POSITIVE LOGITS
    naires
    1.31
     questions
    1.19
     Questions
    1.15
    naire
    1.04
     unanswered
    0.89
     question
    0.88
     answered
    0.81
    Questions
    0.81
     probing
    0.80
     arises
    0.79
    Act Density 0.022%

    No Known Activations