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

    Neuronpedia

    INDEX
    Explanations

    specific prepositions and their variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.26
     purpoſe
    -1.10
     Theſe
    -1.08
     Cæsar
    -1.07
     myſelf
    -1.05
     himſelf
    -1.04
     propOrder
    -1.02
     ſtate
    -1.00
     themſelves
    -0.98
     neceſſ
    -0.98
    POSITIVE LOGITS
     по
    2.73
    По
    1.86
    по
    1.69
     По
    1.64
     ПО
    1.22
     po
    0.98
     theo
    0.98
     לפי
    0.94
    ПО
    0.92
    theo
    0.87
    Act Density 0.018%

    No Known Activations