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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation involving bracket or brace symbols

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    o
    -0.89
    ा
    -0.70
     to
    -0.68
     
    -0.68
      
    -0.67
    op
    -0.63
     DC
    -0.63
     (
    -0.62
     Mendez
    -0.62
     la
    -0.62
    POSITIVE LOGITS
     Jefus
    1.48
     myſelf
    1.44
     themſelves
    1.38
     himſelf
    1.35
     ſeveral
    1.32
     itſelf
    1.32
     purpoſe
    1.30
     Efq
    1.27
     poffible
    1.27
     pleaſure
    1.27
    Act Density 0.007%

    No Known Activations