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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "After."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    transQ
    -0.51
    GIH
    -0.48
     ſtand
    -0.48
    plaat
    -0.47
     ſta
    -0.47
    KURZBESCHREIBUNG
    -0.47
    mobileqq
    -0.44
     ſch
    -0.44
     ſol
    -0.43
     kasarigan
    -0.43
    POSITIVE LOGITS
     after
    3.56
    after
    3.25
     After
    3.08
    After
    3.00
     AFTER
    2.84
     после
    2.78
     після
    2.72
     dopo
    2.70
     después
    2.66
     après
    2.61
    Act Density 0.183%

    No Known Activations