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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to measurements and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gum
    -0.16
    dera
    -0.15
     mixed
    -0.15
    ennie
    -0.15
    repid
    -0.14
     Gum
    -0.14
     Ming
    -0.14
    trx
    -0.14
     Dense
    -0.14
    ÏĦαι
    -0.14
    POSITIVE LOGITS
    å¬
    0.16
    Filled
    0.16
    bach
    0.15
    _FLUSH
    0.15
    ìŀij
    0.15
     Wahl
    0.15
     Difference
    0.15
    @js
    0.15
    uctor
    0.15
    Difference
    0.15
    Act Density 0.203%

    No Known Activations