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

    Neuronpedia

    INDEX
    Explanations

    phrases related to crime and law enforcement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     gmbh
    -0.81
     etui
    -0.81
    capulco
    -0.78
     benzin
    -0.77
     klat
    -0.76
     fote
    -0.76
     torba
    -0.76
     boks
    -0.75
     hek
    -0.72
    quarelle
    -0.72
    POSITIVE LOGITS
    <bos>
    1.01
     Viene
    0.90
     Şi
    0.84
     Mentre
    0.81
     Quelques
    0.78
     quelqu
    0.77
     Queste
    0.76
    Atsauces
    0.75
    Conheça
    0.74
     Había
    0.73
    Act Density 0.551%

    No Known Activations