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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     queſta
    -0.99
    parsedMessage
    -0.94
    ſcher
    -0.88
     $_"
    -0.85
    transQ
    -0.85
     betweenstory
    -0.85
     faſt
    -0.84
    ſehen
    -0.84
    ſelf
    -0.84
    EndContext
    -0.83
    POSITIVE LOGITS
    1.34
        
    0.71
    0.70
    0.69
    0.69
    0.67
          
    0.54
         
    0.54
       
    0.54
    1
    0.53
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.