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

    Neuronpedia

    INDEX
    Explanations

    elements related to scientific processes and advancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Paglinawan
    -1.04
     مشين
    -1.03
    __':
    -1.02
     myſelf
    -1.01
     purpoſe
    -1.01
     Anſ
    -1.00
     Audiodateien
    -0.99
     Diſ
    -0.99
     ―――――
    -0.98
     Monfieur
    -0.95
    POSITIVE LOGITS
     
    0.76
    ,
    0.76
    ↵
    0.74
    <eos>
    0.72
      
    0.72
     in
    0.69
     again
    0.67
    .
    0.66
     of
    0.63
    ↵↵
    0.63
    Act Density 1.154%

    No Known Activations