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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and various forms of separation within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.20
    :
    -0.15
    ↵
    -0.15
     (
    -0.15
    Ùĭ
    -0.14
     looking
    -0.14
     Out
    -0.13
     automát
    -0.13
    apat
    -0.13
    oxic
    -0.13
    POSITIVE LOGITS
     que
    0.23
    si
    0.18
     cosa
    0.18
     thing
    0.17
    SystemService
    0.17
    cosa
    0.17
     idea
    0.16
    ë°©
    0.16
    )?$
    0.16
    _QUEUE
    0.16
    Act Density 0.041%

    No Known Activations