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

    Neuronpedia

    INDEX
    Explanations

    questions uttered by different individuals

    oai_token-act-pair · gpt-3.5-turbo

    questions that prompt inquiry or clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     endorsements
    -0.71
     shortcuts
    -0.66
     affili
    -0.66
     limb
    -0.62
     surviving
    -0.60
    phas
    -0.60
     spo
    -0.60
    estyle
    -0.59
     bunk
    -0.58
     synchronized
    -0.57
    POSITIVE LOGITS
     asked
    1.74
     asks
    1.71
     inquired
    1.63
     wondered
    1.35
     Asked
    1.35
     quer
    1.34
     Questions
    1.29
     questions
    1.28
     enqu
    1.27
     ask
    1.25
    Act Density 0.091%

    No Known Activations