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

    Neuronpedia

    INDEX
    Explanations

    news releases and statements in a formal context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     swarovski
    -1.67
     hairc
    -1.58
     ecru
    -1.54
     unden
    -1.50
     increa
    -1.49
     eiffel
    -1.44
     fta
    -1.43
     ftu
    -1.43
     desir
    -1.38
     pollut
    -1.38
    POSITIVE LOGITS
     statement
    0.90
    Statement
    0.79
    statement
    0.78
     announcement
    0.75
     Statement
    0.74
     spokesperson
    0.72
     spokesman
    0.70
     spokeswoman
    0.69
     issued
    0.67
     statements
    0.65
    Act Density 0.225%

    No Known Activations