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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ulhu
    -0.92
    osuke
    -0.91
    imaru
    -0.86
    soDeliveryDate
    -0.85
    iop
    -0.83
    ively
    -0.80
    ivity
    -0.79
    ym
    -0.77
    ying
    -0.76
    olved
    -0.75
    POSITIVE LOGITS
    cember
    0.78
    uder
    0.76
     Keys
    0.74
    tti
    0.72
    legal
    0.72
     Canter
    0.69
    igne
    0.68
    Mexico
    0.68
     Rica
    0.67
    ©¶æ¥µ
    0.67
    Act Density 8.044%

    No Known Activations