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

    Neuronpedia

    INDEX
    Explanations

    scientific, medical, and technical terms and concepts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ĸļ
    -1.08
    Ô
    -1.06
     curtains
    -0.96
     footing
    -0.93
    eele
    -0.92
     Amend
    -0.90
     Documents
    -0.88
     Esk
    -0.83
     feder
    -0.82
     curtain
    -0.82
    POSITIVE LOGITS
    Ļ
    1.35
    adelphia
    1.21
    aceutical
    1.20
    ¬
    1.18
    «
    1.15
    ogram
    1.15
    İ
    1.12
    agall
    1.06
    ashtra
    1.04
    ©
    1.04
    Act Density 1.194%

    No Known Activations