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

    Neuronpedia

    INDEX
    Explanations

    references to negotiations or related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -1.23
     myſelf
    -1.21
     whoſe
    -1.18
     raiſ
    -1.15
     Efq
    -1.12
     Monfieur
    -1.12
     againſt
    -1.08
     deſt
    -1.06
     himſelf
    -1.06
     becauſe
    -1.05
    POSITIVE LOGITS
    <h2>
    0.71
     P
    0.60
    <h6>
    0.59
    <eos>
    0.56
     negotiations
    0.56
     I
    0.55
    ↵↵
    0.54
      
    0.50
     "
    0.50
     D
    0.50
    Act Density 0.213%

    No Known Activations