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

    Neuronpedia

    INDEX
    Explanations

    technical jargon related to data structures and messaging frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atron
    -0.17
     Muham
    -0.16
    itez
    -0.16
    ilim
    -0.15
    iju
    -0.15
    meden
    -0.15
     Baghd
    -0.15
    mlink
    -0.14
    "display
    -0.14
    ayd
    -0.14
    POSITIVE LOGITS
     bits
    0.21
    bits
    0.21
     shift
    0.20
    field
    0.19
     shifts
    0.19
     bit
    0.18
    (bits
    0.17
     shifting
    0.17
     Bit
    0.17
    ä½į
    0.16
    Act Density 0.037%

    No Known Activations