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

    Neuronpedia

    INDEX
    Explanations

    mentions of objects being equipped with specific components or features

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fitted" and related terms, indicating a focus on equipment and installation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udi
    -0.78
     boycott
    -0.69
     stal
    -0.67
    creation
    -0.67
    éĩ
    -0.64
    iot
    -0.62
     Wax
    -0.62
     skepticism
    -0.61
     Americas
    -0.61
     mistakes
    -0.61
    POSITIVE LOGITS
     fitted
    3.80
    fitted
    1.95
     fit
    1.68
     fitting
    1.64
     equipped
    1.59
     fitt
    1.41
    fitting
    1.41
     Fit
    1.30
     suited
    1.30
    fit
    1.27
    Act Density 0.015%

    No Known Activations