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

    Neuronpedia

    INDEX
    Explanations

    statistical data and ranking information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.09
    2:0.04
    3:0.08
    4:0.06
    5:0.10
    6:0.19
    7:0.08
    8:0.03
    9:0.06
    10:0.02
    11:0.12
    Negative Logits
     ObamaCare
    -2.60
    ktop
    -2.39
    aukee
    -2.29
    amacare
    -2.26
    DonaldTrump
    -2.21
     POLITICO
    -2.19
    paio
    -2.16
    olitics
    -2.16
     shutdown
    -2.15
    pport
    -2.14
    POSITIVE LOGITS
     Originally
    2.47
    ".[
    2.33
    Originally
    2.30
    Contents
    2.27
     Whilst
    2.27
    ).[
    2.11
    During
    2.07
     Additionally
    2.07
    Notable
    2.06
     Various
    1.98
    Act Density 0.031%

    No Known Activations