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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "through."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    passage through places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    paravant
    -0.51
    tableFuture
    -0.50
     fós
    -0.50
     enfans
    -0.48
     sièges
    -0.47
     bookId
    -0.47
     doméstico
    -0.47
     ſtill
    -0.46
     larmes
    -0.46
     Tatsache
    -0.46
    POSITIVE LOGITS
    through
    1.41
     through
    1.39
     THROUGH
    1.31
     Through
    1.31
    Through
    1.30
    Thru
    1.18
    THROUGH
    1.16
     Thru
    1.11
     thru
    1.10
    thru
    1.02
    Act Density 0.047%

    No Known Activations