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

    Neuronpedia

    INDEX
    Explanations

    references to political figures or affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
      
    -0.66
     ataupun
    -0.55
    ,
    -0.52
     oppure
    -0.47
     iż
    -0.45
     besitzt
    -0.45
     mempunyai
    -0.44
     mengenai
    -0.43
       
    -0.43
    ...
    -0.43
    POSITIVE LOGITS
     XNUMX
    1.41
     myſelf
    1.40
    NUMX
    1.36
     purpoſe
    1.30
     itſelf
    1.24
     Monfieur
    1.23
     Jefus
    1.23
     pleaſure
    1.22
     whoſe
    1.22
     becauſe
    1.20
    Act Density 0.038%

    No Known Activations