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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various societal issues and concepts such as political strategy, governmental practices, and social norms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     externi
    -0.65
    Datuak
    -0.65
     CiNii
    -0.63
    OGND
    -0.63
     persino
    -0.60
     perciò
    -0.60
    Билгалдахарш
    -0.57
     esattamente
    -0.57
    zarchiwizowane
    -0.56
    Cechy
    -0.56
    POSITIVE LOGITS
     dinas
    0.48
     alip
    0.45
     jawa
    0.45
     karna
    0.44
     saar
    0.43
     saad
    0.43
     wali
    0.43
     tuta
    0.42
     maske
    0.42
     xdrive
    0.40
    Act Density 1.108%

    No Known Activations