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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the number "two" and related phrases indicating quantity or pairings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pie
    -0.15
    222
    -0.15
    bach
    -0.14
    urg
    -0.14
    iets
    -0.14
    ERA
    -0.14
    kı
    -0.14
     ruce
    -0.14
    ART
    -0.14
    loe
    -0.14
    POSITIVE LOGITS
    .appspot
    0.17
    aje
    0.15
    etest
    0.15
     매
    0.14
    itest
    0.14
     ISIL
    0.13
    addon
    0.13
    ely
    0.13
    lick
    0.13
    ãĤĨ
    0.13
    Act Density 0.068%

    No Known Activations