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

    Neuronpedia

    INDEX
    Explanations

    whitespace characters and their surrounding context in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegistryLite
    -0.59
    <eos>
    -0.58
    and
    -0.57
     of
    -0.55
    with
    -0.52
    C
    -0.52
    de
    -0.51
    Numerology
    -0.50
     OMIT
    -0.50
    l
    -0.50
    POSITIVE LOGITS
     pleaſure
    0.86
    amaño
    0.77
     ſmall
    0.74
    enumi
    0.74
    adeloupe
    0.73
     تضيفلها
    0.72
     Majefty
    0.70
    adecimal
    0.70
    ⃣
    0.69
     greateſt
    0.69
    Act Density 0.425%

    No Known Activations