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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and structural elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estekak
    -0.69
     ProtoMessage
    -0.63
    NameInMap
    -0.63
     dAtA
    -0.62
    Diwedd
    -0.60
    EndInit
    -0.60
     disambiguazione
    -0.59
    verifyException
    -0.58
    PerformLayout
    -0.58
     незавершена
    -0.58
    POSITIVE LOGITS
    tiérrez
    0.38
     symmetrical
    0.35
     رابط
    0.34
     what
    0.34
     asymmetrical
    0.33
     trades
    0.33
     mutable
    0.33
    AsString
    0.33
     intuitive
    0.32
     armed
    0.32
    Act Density 0.288%

    No Known Activations