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

    Neuronpedia

    INDEX
    Explanations

    references to scientific papers or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asser
    -0.17
    trag
    -0.16
     Shack
    -0.15
    åľŃ
    -0.15
    éº
    -0.15
    odus
    -0.15
    arty
    -0.15
    ERM
    -0.14
    unch
    -0.14
    SizePolicy
    -0.14
    POSITIVE LOGITS
    apes
    0.16
    sen
    0.15
    TOTYPE
    0.15
    fe
    0.15
    fits
    0.14
    iaz
    0.14
    ekce
    0.14
    ç¶
    0.14
    feb
    0.14
    ky
    0.14
    Act Density 0.059%

    No Known Activations