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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts pertaining to equality and civil rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.07
    3:0.15
    4:0.02
    5:0.03
    6:0.15
    7:0.18
    8:0.04
    9:0.07
    10:0.08
    11:0.11
    Negative Logits
     pad
    -1.07
    ROR
    -1.04
    sov
    -1.04
     upd
    -1.01
     torped
    -1.00
    \/\/
    -1.00
    lder
    -0.99
     rink
    -0.97
     craw
    -0.94
    hift
    -0.94
    POSITIVE LOGITS
    equality
    1.45
     Equality
    1.37
    ailability
    1.26
     equality
    1.25
    gnu
    1.19
    iannopoulos
    1.13
    cellence
    1.10
    amacare
    1.08
    hammad
    1.07
    ioxide
    1.06
    Act Density 0.031%

    No Known Activations