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

    Neuronpedia

    INDEX
    Explanations

    references to the word "One" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lich
    -0.15
    rene
    -0.15
    heimer
    -0.15
    sc
    -0.15
    utable
    -0.14
    _unicode
    -0.14
    sets
    -0.14
    sm
    -0.14
    ãĥ¼ãĥĨ
    -0.14
    usive
    -0.13
    POSITIVE LOGITS
    onta
    0.25
    iros
    0.21
    idas
    0.21
     Direction
    0.20
    jeme
    0.18
    illin
    0.18
    ToOne
    0.17
    hung
    0.17
     Stop
    0.17
     Fle
    0.17
    Act Density 0.031%

    No Known Activations