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

    Neuronpedia

    INDEX
    Explanations

    details or descriptions related to fictional concepts or narratives

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     mosqu
    -0.79
     adolesc
    -0.69
     exting
    -0.69
     horizont
    -0.69
     Trinidad
    -0.69
     residence
    -0.68
     partnerships
    -0.62
    ãĥīãĥ©ãĤ´ãĥ³
    -0.61
     partnership
    -0.61
     conclud
    -0.61
    POSITIVE LOGITS
    needed
    1.02
    really
    0.91
    âĹ¼
    0.90
    pires
    0.89
    else
    0.89
    said
    0.87
    you
    0.84
    ever
    0.82
    dust
    0.79
    ebook
    0.79
    Act Density 1.753%

    No Known Activations