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

    Neuronpedia

    INDEX
    Explanations

    names and references related to international organizations and diplomatic entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.19
    3:0.09
    4:0.13
    5:0.03
    6:0.03
    7:0.21
    8:0.03
    9:0.03
    10:0.08
    11:0.11
    Negative Logits
     sailors
    -1.83
     salute
    -1.83
     cruise
    -1.78
     embargo
    -1.74
     rede
    -1.73
     astronauts
    -1.73
     annexed
    -1.72
     leftover
    -1.70
     cherished
    -1.66
     manoeuv
    -1.65
    POSITIVE LOGITS
    tor
    1.82
    urb
    1.78
    oir
    1.70
     RJ
    1.66
    street
    1.65
    gres
    1.62
    alty
    1.58
    /,
    1.57
    ojure
    1.57
    RC
    1.56
    Act Density 0.001%

    No Known Activations