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

    Neuronpedia

    INDEX
    Explanations

    criticisms of social justice movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.04
    2:0.11
    3:0.10
    4:0.11
    5:0.15
    6:0.03
    7:0.14
    8:0.07
    9:0.02
    10:0.04
    11:0.07
    Negative Logits
    ilage
    -1.90
    isine
    -1.84
    atoon
    -1.82
    ocry
    -1.82
    ˈ
    -1.80
    ciation
    -1.80
    ftime
    -1.78
    エル
    -1.78
    bledon
    -1.76
    ophe
    -1.76
    POSITIVE LOGITS
     trillions
    2.89
     democratically
    2.52
     democr
    2.43
     imperialist
    2.43
     whistleblowers
    2.39
     neoliberal
    2.32
     THEIR
    2.26
     billions
    2.26
     impover
    2.23
     Governments
    2.21
    Act Density 1.545%

    No Known Activations