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

    Neuronpedia

    INDEX
    Explanations

    repeated characters or sequences in phrases

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ,
    -0.55
    :
    -0.49
    ;
    -0.48
    setcounter
    -0.46
     //
    -0.46
    wag
    -0.44
     (
    -0.43
     ;
    -0.43
      
    -0.42
     in
    -0.41
    POSITIVE LOGITS
     Monfieur
    1.13
     myſelf
    0.98
     Majefty
    0.95
     iſt
    0.91
    DockStyle
    0.90
    ſelf
    0.89
     pleaſure
    0.88
    MigrationBuilder
    0.87
     ་་
    0.85
     ویکی‌پدیا
    0.84
    Act Density 0.027%

    No Known Activations