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

    Neuronpedia

    INDEX
    Explanations

    recurring themes and time-related phrases in descriptions

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

    frequency and time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.60
    цездатний
    -0.50
     تضيفلها
    -0.48
    رشف
    -0.47
     otomatig
    -0.44
    IsContent
    -0.44
    RenderAtEndOf
    -0.44
     Exacts
    -0.44
    żdy
    -0.42
     vito
    -0.42
    POSITIVE LOGITS
     itſelf
    0.50
     houſe
    0.49
    explique
    0.44
     referenties
    0.42
    ſelf
    0.41
     ſche
    0.41
     becauſe
    0.40
     Sejarah
    0.39
     myſelf
    0.38
     OGSÅ
    0.38
    Act Density 0.184%

    No Known Activations