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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and certain special character sequences in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    «ĺ
    -0.15
    ahat
    -0.15
    turnstile
    -0.14
    printStats
    -0.14
    eyse
    -0.14
    ekil
    -0.13
    едак
    -0.13
     skuteÄįnÄĽ
    -0.13
     LENG
    -0.13
    .xmlbeans
    -0.13
    POSITIVE LOGITS
    âĢ¦↵
    0.19
    ...↵
    0.15
     in
    0.14
     exclusively
    0.14
     Ingram
    0.14
    Âłin
    0.14
     An
    0.14
     to
    0.13
     inter
    0.13
    âĢ¦
    0.13
    Act Density 0.363%

    No Known Activations