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

    Neuronpedia

    INDEX
    Explanations

    links and URLs within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.11
    1:0.01
    2:0.05
    3:0.16
    4:0.05
    5:0.20
    6:0.04
    7:0.12
    8:0.11
    9:0.02
    10:0.06
    11:0.03
    Negative Logits
     colours
    -2.40
     organisers
    -2.33
     organise
    -2.30
     organisation
    -2.27
     ana
    -2.27
     presenter
    -2.25
     BBC
    -2.19
     selector
    -2.17
    NZ
    -2.16
    POSE
    -2.15
    POSITIVE LOGITS
    rossover
    2.22
     Semin
    2.21
    crime
    2.19
     Libertarian
    2.18
    raz
    2.14
    arijuana
    2.09
    Michigan
    2.08
    nesota
    2.07
     Gators
    2.04
     Medicaid
    2.04
    Act Density 0.005%

    No Known Activations