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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conflict or battle

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     certific
    -0.94
     coerc
    -0.82
    undai
    -0.81
    iaries
    -0.79
     UCHIJ
    -0.79
    osponsors
    -0.78
     WARN
    -0.78
     Marketable
    -0.75
    66666666
    -0.74
    yrics
    -0.73
    POSITIVE LOGITS
    naire
    1.22
     involving
    1.09
     waged
    1.08
     raging
    1.04
    naires
    1.02
    horse
    1.01
    fight
    1.00
     against
    0.98
    hunt
    0.95
    athon
    0.93
    Act Density 1.992%

    No Known Activations