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

    Neuronpedia

    INDEX
    Explanations

    military-related terms and organizational structures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Kleine
    -0.61
    <bos>
    -0.57
     dras
    -0.56
     konk
    -0.55
     fisk
    -0.55
     dek
    -0.55
    Neder
    -0.54
     katal
    -0.54
     kant
    -0.52
     kard
    -0.51
    POSITIVE LOGITS
     inappro
    0.93
     embodi
    0.93
     Darío
    0.92
     hornblende
    0.90
     ecru
    0.89
     Mejía
    0.88
     quartzite
    0.87
     hairc
    0.87
     depic
    0.86
     Mónica
    0.86
    Act Density 0.601%

    No Known Activations