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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .tk
    -0.16
     Orig
    -0.16
    .sav
    -0.15
    avax
    -0.15
    лаж
    -0.15
    ôi
    -0.15
    ุà¸ļ
    -0.15
     Ui
    -0.15
    asn
    -0.14
    nas
    -0.14
    POSITIVE LOGITS
    orado
    0.14
     invested
    0.13
    ridged
    0.13
     Euros
    0.13
    essoa
    0.13
    esson
    0.13
    .UTF
    0.13
    .sync
    0.13
    yling
    0.13
    wards
    0.12
    Act Density 0.161%

    No Known Activations