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

    Neuronpedia

    INDEX
    Explanations

    keywords related to global politics and international agreements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.84
     gagne
    -0.56
     mérite
    -0.54
     soigne
    -0.53
     marte
    -0.53
     boxe
    -0.52
     illustre
    -0.51
     réuss
    -0.51
     horizont
    -0.51
     constate
    -0.50
    POSITIVE LOGITS
     unwarran
    0.62
     coö
    0.60
     Áng
    0.59
     Viene
    0.59
     Darío
    0.57
     Tampoco
    0.57
     McLaugh
    0.56
     souverain
    0.56
     sovere
    0.56
     Exteriores
    0.56
    Act Density 0.532%

    No Known Activations