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

    Neuronpedia

    INDEX
    Explanations

    references to the second person in conversational contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.44
    ricing
    -0.41
     A
    -0.40
     yourself
    -0.40
     the
    -0.39
      
    -0.39
    yourself
    -0.38
     This
    -0.37
     under
    -0.37
     mej
    -0.36
    POSITIVE LOGITS
    ValueStyle
    1.05
    principalTable
    0.98
     autorytatywna
    0.94
     insuffisamment
    0.90
    verifyException
    0.90
    Sucesor
    0.88
     tartalomajánló
    0.86
    GOTREF
    0.85
    DockStyle
    0.84
     виправивши
    0.83
    Act Density 0.066%

    No Known Activations