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

    Neuronpedia

    INDEX
    Explanations

    XML-like structured tags and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.68
    ,
    -0.64
    (
    -0.64
     bur
    -0.62
     (
    -0.61
    )
    -0.57
     En
    -0.56
    "
    -0.55
    ",
    -0.54
     Bur
    -0.54
    POSITIVE LOGITS
     myſelf
    1.09
     itſelf
    1.08
     becauſe
    1.04
     كومونز
    1.02
     ſtate
    1.00
     raiſ
    0.99
     greateſt
    0.96
     uſed
    0.94
     Theſe
    0.94
     feroit
    0.93
    Act Density 0.218%

    No Known Activations