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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "по" and its variations in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.04
     himſelf
    -0.82
     Cæsar
    -0.81
    ImageContext
    -0.78
     Majefty
    -0.77
     purpoſe
    -0.77
     Dase
    -0.77
     propOrder
    -0.77
    例句
    -0.75
     ―――――
    -0.74
    POSITIVE LOGITS
     по
    2.12
    По
    1.64
    по
    1.46
     По
    1.43
     ПО
    1.00
    theo
    0.96
     לפי
    0.95
     po
    0.93
    ПО
    0.90
     за
    0.86
    Act Density 0.026%

    No Known Activations