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

    Neuronpedia

    INDEX
    Explanations

    the phrase "don't forget" and variations of it

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

    don't forget

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.65
    AutoScaleMode
    -0.56
     ویکی‌پدیای
    -0.54
     snippetHide
    -0.49
    دانشنامهٔ
    -0.48
     externi
    -0.48
    SharedCtor
    -0.47
    adaptiveStyles
    -0.47
     ویکی‌پدی
    -0.44
     beginnetje
    -0.43
    POSITIVE LOGITS
     forget
    1.06
     forgot
    1.00
     forgets
    0.97
     forgetting
    0.94
    forget
    0.94
     forgotten
    0.93
     Forget
    0.90
    forgotten
    0.88
     FORGET
    0.87
     забы
    0.82
    Act Density 0.001%

    No Known Activations