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

    Neuronpedia

    INDEX
    Explanations

    specific details and references within a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.22
     myſelf
    -1.03
     themſelves
    -1.01
     Majefty
    -1.01
     fevere
    -1.01
     ſever
    -1.00
     caufe
    -0.99
     Theſe
    -0.98
     cauſe
    -0.98
     faſt
    -0.98
    POSITIVE LOGITS
     I
    0.76
    :
    0.64
    ,
    0.58
     is
    0.56
    <eos>
    0.56
     
    0.54
    ですが
    0.52
    ?
    0.52
    I
    0.52
    というと
    0.51
    Act Density 0.325%

    No Known Activations