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

    Neuronpedia

    INDEX
    Explanations

    punctuation in the text, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    blade
    -0.15
    äºŃ
    -0.15
    rtle
    -0.15
    ä¸ĸç´Ģ
    -0.15
    mage
    -0.14
    celed
    -0.14
    iciel
    -0.14
    ุà¹Ī
    -0.14
    ίγ
    -0.14
    erville
    -0.14
    POSITIVE LOGITS
     by
    0.16
    ome
    0.15
    629
    0.15
    åıĹ
    0.15
     position
    0.14
    uchen
    0.14
     fuse
    0.14
     Dak
    0.14
     in
    0.14
    ABB
    0.14
    Act Density 0.004%

    No Known Activations