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

    Neuronpedia

    INDEX
    Explanations

    technical attributes and parameters in code or markup

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.93
     houſe
    -0.87
     itſelf
    -0.84
     ſtate
    -0.83
     pleaſure
    -0.82
     raiſ
    -0.82
     uſed
    -0.82
     Monfieur
    -0.82
     greateſt
    -0.81
     ſche
    -0.81
    POSITIVE LOGITS
    DoubleQuotes
    0.68
     rowspan
    0.67
    multirow
    0.61
     
    0.57
      
    0.55
     gerek
    0.50
    localctx
    0.49
    <strong>
    0.48
     שוליים
    0.48
    ecap
    0.48
    Act Density 0.015%

    No Known Activations