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

    Neuronpedia

    INDEX
    Explanations

    phrases related to gratitude and acknowledgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [.
    -0.16
    ensburg
    -0.15
     correct
    -0.14
    ilton
    -0.14
    och
    -0.13
    uzzi
    -0.13
    KeyCode
    -0.13
     Witt
    -0.13
    monds
    -0.13
     Cub
    -0.13
    POSITIVE LOGITS
    âĨIJ
    0.47
    Previous
    0.47
    Prev
    0.42
    previous
    0.42
     Previous
    0.41
     Tags
    0.40
     previous
    0.40
    Labels
    0.36
     tags
    0.36
    âŁ
    0.34
    Act Density 0.460%

    No Known Activations