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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'self' and its variations within programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cept
    -0.17
    ettel
    -0.16
    ebin
    -0.16
    antor
    -0.15
    á»Ļ
    -0.14
    alink
    -0.14
    inion
    -0.14
     fir
    -0.14
    rant
    -0.14
    detail
    -0.14
    POSITIVE LOGITS
    urch
    0.14
    å´İ
    0.14
     æı
    0.14
     Christopher
    0.14
    itize
    0.13
    AGO
    0.13
    Chris
    0.13
     *)((
    0.13
     prote
    0.13
    -root
    0.13
    Act Density 0.001%

    No Known Activations