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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "did" along with related actions and inquiries about them

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

    you'd

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    //
    -0.42
     amenaz
    -0.38
     ancaman
    -0.37
    TestingModule
    -0.36
    wakili
    -0.35
     antemano
    -0.35
     recomiendo
    -0.33
    rinfo
    -0.32
     ninguna
    -0.32
    なのは
    -0.32
    POSITIVE LOGITS
    SequentialGroup
    0.57
     PARSER
    0.53
    Notae
    0.52
     fascic
    0.50
     Flyer
    0.50
    moreland
    0.50
     WOULD
    0.49
    bcryptjs
    0.49
     Würde
    0.49
     aDecoder
    0.49
    Act Density 0.019%

    No Known Activations