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

    Neuronpedia

    INDEX
    Explanations

    patterns related to brackets and delimiters in code or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pletion
    -0.15
    olut
    -0.15
    aul
    -0.14
    vous
    -0.14
    ร
    -0.13
    agner
    -0.13
     же
    -0.13
     contemplate
    -0.13
    imitives
    -0.13
    eenth
    -0.13
    POSITIVE LOGITS
    ster
    0.17
    sic
    0.16
    elic
    0.16
     concrete
    0.15
     Concrete
    0.14
    stery
    0.14
    ajar
    0.14
    adia
    0.14
    ippi
    0.14
    stre
    0.14
    Act Density 0.075%

    No Known Activations