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

    Neuronpedia

    INDEX
    Explanations

    syntax elements and symbols commonly used in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .getB
    -0.41
    -b
    -0.38
    "B
    -0.34
    =B
    -0.34
     B
    -0.33
    ÂłB
    -0.32
    .b
    -0.32
    Âłb
    -0.32
    :B
    -0.31
    <B
    -0.30
    POSITIVE LOGITS
    Buffer
    0.21
    _buffer
    0.20
     Boolean
    0.20
    Button
    0.18
     Buffer
    0.18
    _BUFFER
    0.18
    _bool
    0.18
     Bonus
    0.18
    Boolean
    0.18
     billions
    0.18
    Act Density 0.065%

    No Known Activations