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

    Neuronpedia

    INDEX
    Explanations

    references to factual information and its importance in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jan
    -0.64
     ser
    -0.63
     Ser
    -0.58
     Moy
    -0.55
     folks
    -0.55
    <eos>
    -0.55
     et
    -0.54
     ru
    -0.54
     kele
    -0.53
    ↵↵
    -0.53
    POSITIVE LOGITS
     Efq
    0.99
     Fact
    0.94
     greateſt
    0.92
     itſelf
    0.92
     myſelf
    0.89
     Fears
    0.88
     purpoſe
    0.88
     facts
    0.88
    FACT
    0.88
    facts
    0.87
    Act Density 0.183%

    No Known Activations