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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their interactions within the narrative

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

    I followed by verbs and nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.48
    WEBPACK
    -0.44
     <<<<<<<<<<<<<<
    -0.43
     înc
    -0.42
    awtextra
    -0.41
    vium
    -0.40
     Вікі
    -0.40
     Better
    -0.40
    mately
    -0.40
    idable
    -0.40
    POSITIVE LOGITS
     Jefus
    0.50
    Vanjske
    0.47
    ี้ยง
    0.46
     romero
    0.44
     barran
    0.43
    ImageField
    0.41
    Referensi
    0.41
     palvel
    0.41
     gatos
    0.41
     girlfriends
    0.41
    Act Density 0.210%

    No Known Activations