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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news articles, police reports, and civic engagement

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     skelet
    -0.42
     pse
    -0.42
     disadvant
    -0.41
     exting
    -0.38
     UNCLASSIFIED
    -0.38
     welf
    -0.37
     reper
    -0.35
     Azerb
    -0.34
    olitan
    -0.34
     caut
    -0.34
    POSITIVE LOGITS
     âĢİ
    0.49
     [âĢ¦]
    0.46
     âĢº
    0.43
    âĢİ
    0.41
     ....
    0.41
     Posted
    0.40
     ...
    0.38
     Vinyl
    0.36
    20439
    0.36
    0.34
    Act Density 55.338%

    No Known Activations