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

    Neuronpedia

    INDEX
    Explanations

    questions words in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the 'WH' question words, indicating inquiries or prompts related to "who," "what," "where," "when," and "why."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bart
    -0.66
     Grande
    -0.63
     Sunshine
    -0.63
    uating
    -0.62
    uated
    -0.62
     Defenders
    -0.60
     clearance
    -0.60
     advance
    -0.60
     Bucks
    -0.59
     Replay
    -0.59
    POSITIVE LOGITS
    soever
    1.24
    ilst
    1.20
    ispers
    1.09
    olly
    1.04
    istle
    1.00
    ipl
    0.95
    irlwind
    0.94
    itness
    0.93
    ither
    0.90
    oles
    0.90
    Act Density 0.009%

    No Known Activations