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

    Neuronpedia

    INDEX
    Explanations

    questions or queries

    oai_token-act-pair · gpt-3.5-turbo

    inquiries or questions that provoke thought or discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rites
    -0.74
    onz
    -0.71
    events
    -0.63
     corrid
    -0.63
    odka
    -0.60
     Overview
    -0.59
    gian
    -0.58
     promotions
    -0.58
    lett
    -0.58
    ufact
    -0.58
    POSITIVE LOGITS
    naires
    1.46
     mark
    1.26
    naire
    1.15
     arises
    1.08
     unanswered
    1.05
     posed
    1.03
    mark
    1.02
     answered
    0.92
     marks
    0.91
     asked
    0.91
    Act Density 0.047%

    No Known Activations