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

    Neuronpedia

    INDEX
    Explanations

    punctuation and basic sentence structure patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ear
    -0.15
    ocked
    -0.15
    ockey
    -0.15
    殿
    -0.14
     oh
    -0.14
    åĩ¡
    -0.14
     vig
    -0.14
     peer
    -0.14
     aside
    -0.14
    ches
    -0.13
    POSITIVE LOGITS
     therefore
    0.19
     accordingly
    0.19
     Accordingly
    0.19
    为äºĨ
    0.18
     Therefore
    0.18
    Therefore
    0.17
    ï¼ĮæīĢ以
    0.17
    iban
    0.17
    dit
    0.16
     Ä°ÅŁte
    0.16
    Act Density 0.146%

    No Known Activations