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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ican
    -0.16
     Aberdeen
    -0.15
    KHR
    -0.15
    ãģ¬
    -0.15
    ¹Ħ
    -0.15
    pute
    -0.15
    ãĥ¼ãĥĭ
    -0.14
     oslo
    -0.14
    ncia
    -0.14
    cio
    -0.14
    POSITIVE LOGITS
     à¸Ľà¸£à¸°à¹Ģà¸Ĺศ
    0.29
     Italy
    0.20
     Australia
    0.20
     Germany
    0.20
     Spain
    0.20
     England
    0.20
     Ontario
    0.18
     Republic
    0.18
     Poland
    0.17
     Ireland
    0.17
    Act Density 0.134%

    No Known Activations