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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negotiations and treaty processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ettel
    -0.16
    inho
    -0.15
    oulos
    -0.15
     Kul
    -0.15
    aña
    -0.14
    ughty
    -0.14
    inate
    -0.14
     ÄĮeské
    -0.14
    .toolbox
    -0.14
     Society
    -0.13
    POSITIVE LOGITS
     iron
    0.22
     hammer
    0.20
     broker
    0.20
     gal
    0.20
     push
    0.18
    omentum
    0.18
     Broker
    0.17
     clin
    0.17
     find
    0.17
    Broker
    0.17
    Act Density 0.097%

    No Known Activations