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

    Neuronpedia

    INDEX
    Explanations

    specific instances, locations, or references in arguments and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allet
    -0.16
    ahn
    -0.15
     Dawson
    -0.15
    ãn
    -0.14
    FG
    -0.14
     AUX
    -0.14
    ÎŃÏģα
    -0.13
    uling
    -0.13
     aux
    -0.13
    aux
    -0.13
    POSITIVE LOGITS
     expense
    0.24
     glance
    0.23
     level
    0.21
     Expense
    0.21
     discretion
    0.20
     intervals
    0.20
    expense
    0.19
     odds
    0.19
     disposal
    0.18
     least
    0.18
    Act Density 0.534%

    No Known Activations