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

    Neuronpedia

    INDEX
    Explanations

    references to the word "one" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ReturnType
    -0.17
    iage
    -0.15
    se
    -0.15
    ãģĦãģ§
    -0.15
    Updates
    -0.15
    inges
    -0.15
    ovice
    -0.14
    agen
    -0.14
    aura
    -0.14
    hind
    -0.14
    POSITIVE LOGITS
     liners
    0.23
     dimensional
    0.18
    mdb
    0.16
    jeme
    0.16
    957
    0.15
    -hit
    0.15
    ÑĭÑĪ
    0.15
     hell
    0.15
    percent
    0.14
    -nil
    0.14
    Act Density 0.064%

    No Known Activations