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

    Neuronpedia

    INDEX
    Explanations

    words related to diplomatic relations and international politics, especially between specific countries

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    utory
    -0.61
     Psal
    -0.58
    Condition
    -0.56
    tun
    -0.56
     Dhabi
    -0.55
    vich
    -0.54
    humane
    -0.54
     funeral
    -0.53
    racuse
    -0.53
     Blessing
    -0.53
    POSITIVE LOGITS
     sexes
    0.95
    paces
    0.92
     halves
    0.86
     simultaneously
    0.84
     respectively
    0.76
    ixt
    0.76
    agos
    0.74
    hips
    0.74
     alike
    0.73
    pring
    0.70
    Act Density 8.344%

    No Known Activations