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

    Neuronpedia

    INDEX
    Explanations

    numerical data and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The number 9 followed by other numbers

    np_acts-logits-general · gemini-2.0-flash

    digit 9

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.64
    ↵↵
    -0.58
     Tr
    -0.58
    ↵
    -0.55
     (
    -0.53
      
    -0.52
    ,
    -0.52
     an
    -0.51
     tr
    -0.51
     a
    -0.50
    POSITIVE LOGITS
     myſelf
    1.32
     himſelf
    1.20
     raiſ
    1.19
     itſelf
    1.15
     Monfieur
    1.13
     ſta
    1.13
     Jefus
    1.11
     themſelves
    1.11
     Majefty
    1.11
     ſeveral
    1.10
    Act Density 0.683%

    No Known Activations