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

    Neuronpedia

    INDEX
    Explanations

    various types of quotation marks and assignment symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieg
    -0.15
    ittle
    -0.15
    lil
    -0.15
    Ú¯ÙĦ
    -0.14
    laps
    -0.14
    addons
    -0.14
    ISTA
    -0.13
     refinery
    -0.13
    ês
    -0.12
    lane
    -0.12
    POSITIVE LOGITS
    osas
    0.18
     Mercer
    0.14
    vice
    0.14
    ække
    0.14
     Essen
    0.14
    andise
    0.14
    ouble
    0.13
    otton
    0.13
    _dependencies
    0.13
    .tem
    0.13
    Act Density 0.031%

    No Known Activations