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

    Neuronpedia

    INDEX
    Explanations

    statistical or computational terms and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.55
     te
    -0.52
      
    -0.51
     lo
    -0.49
    ,
    -0.47
     je
    -0.45
     Four
    -0.43
     l
    -0.42
     hit
    -0.42
     mar
    -0.42
    POSITIVE LOGITS
    ViewImports
    0.93
     ་་
    0.93
     itſelf
    0.92
     للمعارف
    0.92
    AsUp
    0.89
     Cæsar
    0.88
     myſelf
    0.84
     auffi
    0.83
     Monfieur
    0.80
    IsContent
    0.80
    Act Density 0.429%

    No Known Activations