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

    Neuronpedia

    INDEX
    Explanations

    frequent function words and conjunctions that suggest sentence structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç¯ĩ
    -0.16
    å°¿
    -0.16
    engin
    -0.16
    Ä°Y
    -0.15
     Seymour
    -0.14
    .Îij
    -0.14
    ednou
    -0.14
     Spin
    -0.14
     DeepCopy
    -0.14
    jang
    -0.14
    POSITIVE LOGITS
     Wilde
    0.17
     Lies
    0.16
    ught
    0.16
     Republic
    0.15
    jo
    0.15
     (
    0.15
     selection
    0.15
    otics
    0.14
    english
    0.14
    0.14
    Act Density 0.001%

    No Known Activations