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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate dependence or reliance on external factors or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imson
    -0.16
    ynchronously
    -0.15
    .misc
    -0.15
    yna
    -0.14
    enheim
    -0.14
    å¼¹
    -0.14
    criptor
    -0.14
    ãĥ³ãĤ¿
    -0.14
    .utf
    -0.14
     gì
    -0.14
    POSITIVE LOGITS
     sources
    0.15
    agers
    0.15
     ability
    0.15
    396
    0.15
     careful
    0.14
     chains
    0.14
     kaynaģı
    0.14
    578
    0.14
    azen
    0.14
     supply
    0.14
    Act Density 0.064%

    No Known Activations