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

    Neuronpedia

    INDEX
    Explanations

    phrases related to politics, military operations, and historical events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     horm
    -0.46
     glim
    -0.46
     helic
    -0.45
     charism
    -0.45
     Gors
    -0.43
     cryst
    -0.42
     rul
    -0.41
    Font
    -0.41
     Siber
    -0.41
     caut
    -0.41
    POSITIVE LOGITS
     lasted
    0.47
    imity
    0.45
     simultaneously
    0.45
     celebrated
    0.44
     involving
    0.44
     successfully
    0.43
     perv
    0.43
    ãĤĴ
    0.43
     reverber
    0.41
     relating
    0.41
    Act Density 5.671%

    No Known Activations