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

    Neuronpedia

    INDEX
    Explanations

    references related to Poland

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    undai
    -1.05
    querque
    -1.04
    ---------------
    -0.94
    gered
    -0.93
    uilt
    -0.90
    Ü
    -0.89
    isitions
    -0.89
    rained
    -0.89
    ahime
    -0.88
    inous
    -0.87
    POSITIVE LOGITS
     Pact
    1.12
    ÅĤ
    1.08
    oslov
    0.91
     Mehran
    0.90
    cz
    0.89
    istani
    0.82
     Animation
    0.81
    inski
    0.79
    Union
    0.79
     Warsaw
    0.79
    Act Density 1.048%

    No Known Activations