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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Le" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ewig
    -0.38
     olvides
    -0.35
     Innenstadt
    -0.32
     confronted
    -0.32
     Grünen
    -0.31
     assaults
    -0.30
     Unters
    -0.29
     clashes
    -0.29
     Baumwolle
    -0.28
     censiti
    -0.28
    POSITIVE LOGITS
    UnusedPrivate
    0.67
     queſta
    0.61
     endfor
    0.57
     geſch
    0.57
     ſta
    0.54
     myſelf
    0.54
     $_(
    0.54
    cheria
    0.53
    parsedMessage
    0.53
     $_[
    0.52
    Act Density 0.188%

    No Known Activations