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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and military contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ftu
    -1.65
     fta
    -1.63
     aen
    -1.56
     sappi
    -1.54
     ftre
    -1.54
     vns
    -1.54
     fatis
    -1.53
     poff
    -1.48
     hcm
    -1.46
     desir
    -1.46
    POSITIVE LOGITS
     And
    0.97
    And
    0.88
     yes
    0.78
     yet
    0.78
     because
    0.74
     even
    0.73
     if
    0.70
     then
    0.69
     while
    0.69
     But
    0.69
    Act Density 0.140%

    No Known Activations