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

    Neuronpedia

    INDEX
    Explanations

    numbers and technical terms or jargon related to defense, health, politics, and other complex subjects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to government actions and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.03
    2:0.06
    3:0.04
    4:0.04
    5:0.11
    6:0.09
    7:0.13
    8:0.04
    9:0.08
    10:0.18
    11:0.08
    Negative Logits
     ­
    -0.95
    ).[
    -0.95
    )].
    -0.95
    ."[
    -0.94
    .[
    -0.92
    ".[
    -0.90
    ,[
    -0.89
     theirs
    -0.85
    "[
    -0.85
     respectively
    -0.80
    POSITIVE LOGITS
    yip
    1.25
    maxwell
    1.05
    xual
    1.04
    DragonMagazine
    1.00
    ��
    0.98
    arte
    0.93
    quished
    0.93
    ギ
    0.92
    ディ
    0.90
    PDATE
    0.88
    Act Density 0.199%

    No Known Activations