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

    Neuronpedia

    INDEX
    Explanations

    references to the word "the" and variations of personal pronouns

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

    determiners followed by ordinals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Round
    -0.28
     Ext
    -0.28
     Step
    -0.27
     ARTICLE
    -0.27
    риев
    -0.26
    HasBeenSet
    -0.26
    Step
    -0.26
    Future
    -0.26
    ITER
    -0.26
    Pog
    -0.26
    POSITIVE LOGITS
     first
    1.09
     second
    1.08
     third
    0.98
     tweede
    0.96
     last
    0.94
     fourth
    0.92
     derde
    0.90
     fifth
    0.86
     pertama
    0.85
     eerste
    0.85
    Act Density 0.132%

    No Known Activations