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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ære
    -0.18
    CHASE
    -0.15
    ær
    -0.15
    aggio
    -0.15
    ADI
    -0.15
     detriment
    -0.15
    stead
    -0.14
    piler
    -0.14
    tle
    -0.14
    zk
    -0.14
    POSITIVE LOGITS
    lava
    0.16
    pson
    0.15
    ãİ
    0.15
    digest
    0.15
    anda
    0.15
    slash
    0.14
    lyn
    0.14
    _unpack
    0.14
     âĵĺ
    0.14
     comando
    0.14
    Act Density 0.034%

    No Known Activations