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

    Neuronpedia

    INDEX
    Explanations

    formatted whitespace and its associated values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -1.09
    InjectAttribute
    -1.06
    -1.02
     Majefty
    -1.01
    Vidite
    -0.91
     HasFactory
    -0.91
    Portály
    -0.90
     fubject
    -0.89
     feroit
    -0.88
     reaſon
    -0.87
    POSITIVE LOGITS
     
    0.58
      
    0.56
    们
    0.52
    </u>
    0.51
     main
    0.50
    пас
    0.50
     Main
    0.50
     S
    0.48
     ins
    0.47
    0.47
    Act Density 0.074%
    No Known Activations