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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to Finland and institutions within it

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     saks
    -0.90
     pank
    -0.87
     syd
    -0.82
     kys
    -0.81
    Läh
    -0.81
     elek
    -0.80
     kog
    -0.79
     makro
    -0.78
     alko
    -0.77
     maksi
    -0.76
    POSITIVE LOGITS
     disagre
    1.62
     impra
    1.59
     unwarran
    1.56
     excru
    1.56
     increa
    1.55
     depic
    1.54
     shenan
    1.50
     maneu
    1.48
     reluct
    1.46
     indestru
    1.46
    Act Density 0.123%

    No Known Activations