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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation, particularly quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fibers
    -0.91
    ing
    -0.85
    orrhea
    -0.82
     Ortiz
    -0.80
     gages
    -0.78
     gage
    -0.76
    mtext
    -0.76
     fapt
    -0.75
    Reis
    -0.73
    ς
    -0.72
    POSITIVE LOGITS
    "><?=
    1.16
    verwijspagina
    1.11
     moulds
    1.09
    ategorised
    1.01
     analyse
    0.98
     localised
    0.96
    ourable
    0.94
    %",
    0.93
     Organiser
    0.93
    )",
    0.93
    Act Density 0.123%

    No Known Activations