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

    Neuronpedia

    INDEX
    Explanations

    special characters and their repeated patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.70
    USTIN
    -0.62
     estimés
    -0.61
    .
    -0.60
      
    -0.60
    ↵↵
    -0.59
     (
    -0.59
    ar
    -0.59
    ,
    -0.57
    -
    -0.57
    POSITIVE LOGITS
     ainfi
    1.17
     feroit
    1.09
     avoient
    1.05
     auroit
    1.03
     plufieurs
    1.03
     auffi
    1.02
     myſelf
    1.00
     raiſ
    0.97
     pouvoit
    0.96
     juſt
    0.95
    Act Density 0.702%

    No Known Activations