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

    Neuronpedia

    INDEX
    Explanations

    punctuation, particularly commas and semicolons, which indicate structure and separation in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    again
    -0.15
    uing
    -0.15
     Huff
    -0.15
    ãĤ¤ãĥ³ãĥĪ
    -0.14
    etu
    -0.14
    usz
    -0.14
     specifically
    -0.13
    ique
    -0.13
     again
    -0.13
    y
    -0.13
    POSITIVE LOGITS
    -exclusive
    0.19
    clusive
    0.18
     exclusive
    0.17
    exclusive
    0.17
    CLUSIVE
    0.17
    /cgi
    0.17
    klad
    0.16
     being
    0.15
    gle
    0.15
    æµľ
    0.15
    Act Density 0.179%

    No Known Activations