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

    Neuronpedia

    INDEX
    Explanations

    questions being asked or mentioned in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to asking questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    argon
    -0.67
     quotation
    -0.65
    cknow
    -0.64
    enne
    -0.60
     contingency
    -0.59
     spons
    -0.59
    itten
    -0.58
    stood
    -0.58
    alin
    -0.57
    gel
    -0.57
    POSITIVE LOGITS
     whilst
    0.87
     efficiently
    0.81
    enium
    0.80
     wisely
    0.80
     onstage
    0.79
     responsibly
    0.79
     abroad
    0.78
     outdoors
    0.77
     while
    0.75
     concurrently
    0.75
    Act Density 0.567%

    No Known Activations