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

    Neuronpedia

    INDEX
    Explanations

    phrases related to military threats or strategic considerations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ferdin
    -0.71
     erk
    -0.68
     traktor
    -0.66
     bera
    -0.63
     heti
    -0.63
     pank
    -0.60
     saar
    -0.60
     akut
    -0.58
     Öster
    -0.57
     Jä
    -0.57
    POSITIVE LOGITS
    <bos>
    0.57
    Personensuche
    0.56
     hvit
    0.49
     zc
    0.47
     cherchez
    0.47
     Bekasi
    0.47
     voyons
    0.47
     nmax
    0.46
     devaient
    0.46
     découver
    0.45
    Act Density 0.187%

    No Known Activations