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

    Neuronpedia

    INDEX
    Explanations

    countries, agreements, and international relations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     gore
    -0.81
    omaly
    -0.80
     Anarchy
    -0.79
    punk
    -0.77
     subdivision
    -0.73
     Penalty
    -0.72
    BIP
    -0.72
     Shotgun
    -0.70
     BELOW
    -0.69
     Decay
    -0.69
    POSITIVE LOGITS
     Lavrov
    1.25
     ambassadors
    1.24
     deleg
    1.22
     delegation
    1.21
     diplomats
    1.21
     envoy
    1.18
     diplomatic
    1.15
    plom
    1.14
     bilateral
    1.13
    assador
    1.13
    Act Density 0.767%

    No Known Activations