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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
      
    -0.77
     
    -0.74
    <eos>
    -0.70
     Cor
    -0.70
    ↵↵
    -0.66
    <em>
    -0.64
     за
    -0.62
       
    -0.62
    ↵
    -0.60
     Mar
    -0.60
    POSITIVE LOGITS
     myſelf
    1.46
    Datuak
    1.25
     raiſ
    1.23
     doubtnut
    1.22
     Majefty
    1.21
     Monfieur
    1.21
     himſelf
    1.21
     itſelf
    1.21
     ―――――
    1.18
     poffible
    1.17
    Act Density 0.588%

    No Known Activations