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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases or references to "the" in various contexts

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

    Occurrences after the word "the"

    np_acts-logits-general · gemini-2.0-flash

    the + specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fascism
    -0.81
     Phry
    -0.79
     Philist
    -0.77
     zoude
    -0.77
     zelve
    -0.76
     Cister
    -0.75
     Esau
    -0.75
     Athenians
    -0.75
     Mahomet
    -0.74
     مشين
    -0.73
    POSITIVE LOGITS
     same
    1.30
     entire
    1.21
     most
    1.09
     rest
    1.04
     latter
    1.02
     final
    1.01
     various
    0.98
     usual
    0.97
     vast
    0.96
    "):
    0.95
    Act Density 2.944%

    No Known Activations