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

    Neuronpedia

    INDEX
    Explanations

    the word "possession" and sometimes the word "government" and words about time.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     the
    -0.87
     a
    -0.70
     
    -0.67
     their
    -0.64
     an
    -0.59
    expandindo
    -0.58
      
    -0.58
    brainly
    -0.56
     A
    -0.56
     his
    -0.56
    POSITIVE LOGITS
     Jefus
    1.42
     Reſ
    1.41
     Majefty
    1.38
     Diſ
    1.34
     itſelf
    1.30
     Monfieur
    1.29
     myſelf
    1.28
     whoſe
    1.27
     himſelf
    1.25
     faſt
    1.25
    Act Density 0.941%

    No Known Activations