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

    Neuronpedia

    INDEX
    Explanations

    references to the number "one" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ReturnType
    -0.17
    iage
    -0.16
    ãĤĤãģ£ãģ¨
    -0.15
    se
    -0.15
    aura
    -0.15
    inges
    -0.15
     Antar
    -0.14
     cách
    -0.14
    Updates
    -0.14
    enny
    -0.14
    POSITIVE LOGITS
     liners
    0.18
     hell
    0.18
    hell
    0.17
    HELL
    0.15
     Hell
    0.15
    jeme
    0.15
    -nil
    0.15
    -hit
    0.15
    mdb
    0.15
    liner
    0.14
    Act Density 0.060%

    No Known Activations