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

    Neuronpedia

    INDEX
    Explanations

    numerals and references to time periods or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourn
    -0.20
    aeper
    -0.16
    arias
    -0.16
    èį
    -0.15
    irected
    -0.14
    976
    -0.14
    isiyle
    -0.14
    leftJoin
    -0.14
    lica
    -0.14
    .scalablytyped
    -0.14
    POSITIVE LOGITS
    orman
    0.17
    PRS
    0.15
     Gloss
    0.15
     remaining
    0.14
    oman
    0.14
     latest
    0.14
    rog
    0.14
    евиÑĩ
    0.14
    -fold
    0.13
    ecta
    0.13
    Act Density 0.122%

    No Known Activations