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

    Neuronpedia

    INDEX
    Explanations

    text related to advertising or promotions

    oai_token-act-pair · gemini-2.0-flash

    forms of the word 'remember'

    np_token-act-pair-logits · gpt-4o-mini

    Remember

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Atsauces
    -0.77
     itſelf
    -0.75
    urlpatterns
    -0.72
     referenties
    -0.70
    HideFlags
    -0.69
    setupUi
    -0.68
     allAfrica
    -0.66
     myſelf
    -0.66
     iſt
    -0.64
    دانشنامهٔ
    -0.64
    POSITIVE LOGITS
     remember
    1.60
     Remember
    1.48
    Remember
    1.38
    remember
    1.34
     REMEMBER
    1.30
     remembered
    1.13
     remembers
    1.06
     remembering
    1.01
     ricord
    0.93
     nhớ
    0.92
    Act Density 3.583%

    No Known Activations