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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions of electronic components and their functions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    </strong>
    -0.69
      
    -0.54
    !
    -0.50
    </em>
    -0.47
     $
    -0.47
     our
    -0.47
     we
    -0.46
     v
    -0.43
     $\
    -0.43
    .,
    -0.43
    POSITIVE LOGITS
     itſelf
    0.90
     Majefty
    0.90
     houſe
    0.87
     fubject
    0.87
     ſeveral
    0.86
     purpoſe
    0.85
     themſelves
    0.85
    setVerticalGroup
    0.83
     ſtate
    0.83
     pleaſure
    0.83
    Act Density 0.334%

    No Known Activations