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

    Neuronpedia

    INDEX
    Explanations

    requests for assistance, feedback, or information on various subjects

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate requests for help or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itual
    -0.67
    dom
    -0.67
    renheit
    -0.65
    UME
    -0.65
    ranean
    -0.65
    inho
    -0.64
    netflix
    -0.64
    vernight
    -0.62
    isible
    -0.61
     Skydragon
    -0.60
    POSITIVE LOGITS
     suggestions
    1.12
     helpful
    1.07
     corrections
    1.02
     suggestion
    0.97
     enlight
    0.95
     useful
    0.93
     additions
    0.92
     Suggest
    0.91
     sugg
    0.90
     clarification
    0.89
    Act Density 0.645%

    No Known Activations