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

    Neuronpedia

    INDEX
    Explanations

    formal mathematical properties and statements related to definitions and theorems

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.51
     Ne
    -0.50
    :
    -0.48
     [
    -0.47
    ברי
    -0.47
    typeparam
    -0.47
     (
    -0.46
      
    -0.45
     s
    -0.45
     mode
    -0.45
    POSITIVE LOGITS
     itſelf
    1.20
     myſelf
    1.15
     houſe
    1.13
     purpoſe
    1.11
     pleaſure
    1.06
     laſt
    0.99
     perſon
    0.96
     ſeveral
    0.96
     greateſt
    0.96
     ſtand
    0.94
    Act Density 0.240%

    No Known Activations