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

    Neuronpedia

    INDEX
    Explanations

    symbols and operators in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elson
    -0.18
    ese
    -0.17
    ence
    -0.17
    ric
    -0.17
    utom
    -0.16
    entially
    -0.16
     Snape
    -0.16
    ure
    -0.16
    chan
    -0.15
    rog
    -0.15
    POSITIVE LOGITS
    .SIG
    0.19
    .scalablytyped
    0.18
    mates
    0.15
    ::|
    0.15
    زÙĬز
    0.15
    UnderTest
    0.15
    .ease
    0.15
    nd
    0.14
    ê¶Į
    0.14
    EGIN
    0.14
    Act Density 0.068%

    No Known Activations