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

    Neuronpedia

    INDEX
    Explanations

    code and programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -1.32
     itſelf
    -1.11
     Reſ
    -1.09
     Jefus
    -0.98
     leaſt
    -0.97
     Richelieu
    -0.96
     Diſ
    -0.96
    AndEndTag
    -0.96
     Majefty
    -0.96
    ſelf
    -0.95
    POSITIVE LOGITS
     styled
    1.15
    styled
    1.02
    Styled
    0.76
     Styled
    0.74
     (
    0.68
     a
    0.54
     of
    0.53
    Styling
    0.52
     as
    0.52
    <eos>
    0.52
    Act Density 0.025%

    No Known Activations