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

    Neuronpedia

    INDEX
    Explanations

    references to email communication

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     stadiums
    -0.87
     exhibitions
    -0.76
    "},"
    -0.73
     attractions
    -0.72
    ptions
    -0.70
    addons
    -0.68
     athlet
    -0.67
    ¥µ
    -0.67
     parks
    -0.67
     skyline
    -0.67
    POSITIVE LOGITS
     dated
    1.25
     correspondence
    1.24
     letter
    1.16
     handwritten
    1.16
    Dear
    1.11
     forwarded
    1.08
     letters
    1.06
     addressed
    1.02
     fax
    1.01
     typew
    1.01
    Act Density 0.304%

    No Known Activations