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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "upon."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ing
    -0.87
     I
    -0.71
    -
    -0.67
    4
    -0.67
    1
    -0.64
    8
    -0.63
    3
    -0.63
     B
    -0.62
    2
    -0.61
    ING
    -0.61
    POSITIVE LOGITS
     UPON
    2.72
    upon
    2.68
     upon
    2.64
     Upon
    2.51
    Upon
    2.44
     apon
    1.36
     vpon
    1.23
     thereupon
    1.14
     thereon
    1.09
     whereupon
    0.98
    Act Density 0.048%

    No Known Activations