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

    Neuronpedia

    INDEX
    Explanations

    instances of textual formatting or structure in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.02
     Paglinawan
    -0.99
     Anſ
    -0.98
     wikipagina
    -0.96
     Wiktionnaire
    -0.94
     purpoſe
    -0.93
    /**
    -0.93
     itſelf
    -0.91
    IndentedString
    -0.90
     ſtate
    -0.88
    POSITIVE LOGITS
    ,
    1.07
    .
    1.04
    ↵
    0.98
     
    0.89
    <eos>
    0.80
     of
    0.75
     (
    0.74
    ↵↵
    0.74
     in
    0.73
     and
    0.72
    Act Density 0.385%

    No Known Activations