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

    Neuronpedia

    INDEX
    Explanations

    structured programming elements like brackets, colons, and control flow indicators in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -1.03
     Paglinawan
    -1.01
     Baillargeon
    -0.99
     betweenstory
    -0.99
    tvguidetime
    -0.95
    UserScript
    -0.93
     NSCoder
    -0.91
    -0.91
    InjectAttribute
    -0.90
    RegressionTest
    -0.90
    POSITIVE LOGITS
    ↵
    0.54
    .
    0.53
     in
    0.52
    ,
    0.48
     .
    0.47
    '
    0.46
     of
    0.46
     like
    0.45
     given
    0.44
     hela
    0.44
    Act Density 0.152%

    No Known Activations