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

    Neuronpedia

    INDEX
    Explanations

    instances of specific pronouns and articles

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

    Followed by nouns in informal contexts

    np_acts-logits-general · gemini-2.0-flash

    the instructions, game, problem, post

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ="#"><
    -0.78
     således
    -0.71
     asimismo
    -0.70
     précie
    -0.70
     noodzake
    -0.67
     sağlar
    -0.67
    さまざまな
    -0.66
     ciasc
    -0.66
     pertanto
    -0.65
     largely
    -0.65
    POSITIVE LOGITS
     guy
    1.08
     damn
    0.94
     stupid
    0.92
     thing
    0.91
     whole
    0.90
     WHOLE
    0.88
     darn
    0.81
     pics
    0.80
     dude
    0.80
    whole
    0.80
    Act Density 0.377%

    No Known Activations