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

    Neuronpedia

    INDEX
    Explanations

    inclusive phrases emphasizing totality or collective experiences

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

    "All" followed by pronouns or nouns

    np_acts-logits-general · gemini-2.0-flash

    phrases starting with All

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.63
    NewUrlParser
    -0.56
    RegressionTest
    -0.53
    PANY
    -0.53
    енча
    -0.48
    hängen
    -0.47
    NegativeButton
    -0.47
    WebServlet
    -0.46
    RenderAtEndOf
    -0.46
    fromnode
    -0.46
    POSITIVE LOGITS
     all
    0.61
    прав
    0.60
    mamış
    0.60
    though
    0.59
    исленность
    0.58
    WEBPACK
    0.57
     seems
    0.56
    хь
    0.56
     invitamos
    0.54
    رشف
    0.54
    Act Density 0.112%

    No Known Activations