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

    Neuronpedia

    INDEX
    Explanations

    instances of proper nouns and punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \/\/
    -0.15
    etine
    -0.15
    ied
    -0.15
    yny
    -0.14
    ims
    -0.14
    ãĤ¤ãĥ«
    -0.14
    izens
    -0.14
     Sanct
    -0.14
    acco
    -0.14
    ninger
    -0.13
    POSITIVE LOGITS
    orro
    0.15
    icos
    0.14
    eba
    0.14
     лÑİ
    0.14
     Letters
    0.14
     Carrier
    0.14
     Temper
    0.14
    031
    0.14
    assa
    0.13
    isten
    0.13
    Act Density 0.090%

    No Known Activations