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

    Neuronpedia

    INDEX
    Explanations

    words related to security, crime, and international relations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     PU
    -0.71
     Mechdragon
    -0.70
     couch
    -0.67
     guided
    -0.67
     dust
    -0.67
     protected
    -0.65
     nearest
    -0.64
     compliment
    -0.63
     complete
    -0.60
     exits
    -0.59
    POSITIVE LOGITS
    't
    1.70
    ÃŃ
    1.13
    iting
    1.04
    itely
    1.03
    ited
    0.99
    eness
    0.98
    ´
    0.96
    cest
    0.95
    uts
    0.95
    its
    0.94
    Act Density 0.355%

    No Known Activations