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

    Neuronpedia

    INDEX
    Explanations

    references to boycotts and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.14
    1:0.02
    2:0.19
    3:0.09
    4:0.04
    5:0.12
    6:0.05
    7:0.05
    8:0.12
    9:0.06
    10:0.03
    11:0.03
    Negative Logits
    �
    -2.71
     Paddock
    -2.70
    flow
    -2.58
    Emergency
    -2.52
    Flow
    -2.52
     Ü
    -2.49
     Reincarn
    -2.44
     Prest
    -2.42
     reload
    -2.42
     xp
    -2.39
    POSITIVE LOGITS
     boycott
    6.95
     boycot
    6.50
     BDS
    5.09
     divest
    4.03
     Israeli
    3.63
     apartheid
    3.46
     Israel
    3.32
    heid
    3.30
    cott
    3.22
     Palestine
    3.22
    Act Density 0.033%

    No Known Activations