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

    Neuronpedia

    INDEX
    Explanations

    historical and chronological references related to key events or time periods

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    bos
    -0.78
    BIL
    -0.76
    uploads
    -0.76
    mbuds
    -0.72
    elines
    -0.71
    ="#
    -0.70
    ateral
    -0.68
     liking
    -0.68
    rawdownloadcloneembedreportprint
    -0.67
     Monsters
    -0.67
    POSITIVE LOGITS
     century
    1.45
    century
    1.32
     Century
    1.21
     Amendment
    1.18
    ousand
    1.14
    ulhu
    1.06
    ousands
    1.01
     inning
    0.99
     Dynasty
    0.95
    irteen
    0.91
    Act Density 6.896%

    No Known Activations