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

    Neuronpedia

    INDEX
    Explanations

    instances of words related to automobiles or car-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to automotive technology or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    £
    -0.85
     Wilkinson
    -0.77
    sted
    -0.69
     Towns
    -0.68
    çIJ
    -0.67
    vell
    -0.67
    Scotland
    -0.67
    beard
    -0.65
    acion
    -0.65
    had
    -0.65
    POSITIVE LOGITS
     auto
    3.72
     Auto
    2.67
    auto
    2.62
    Auto
    2.62
     autos
    2.44
     autom
    1.82
     automobile
    1.79
     automotive
    1.67
     AUT
    1.63
     autop
    1.61
    Act Density 0.008%

    No Known Activations