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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the restaurant industry

    oai_token-act-pair · gpt-3.5-turbo

    mentions of restaurants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WAR
    -0.76
    ypes
    -0.70
    Contents
    -0.68
    Ax
    -0.67
     cords
    -0.66
    Mat
    -0.66
    Thom
    -0.65
    clips
    -0.64
    CB
    -0.63
     Wales
    -0.61
    POSITIVE LOGITS
     restaurant
    3.24
     Restaurant
    2.59
     restaurants
    2.59
     Restaur
    2.27
     restaur
    2.22
     diner
    2.13
     café
    1.91
     cafe
    1.88
     eater
    1.85
     dining
    1.79
    Act Density 0.015%

    No Known Activations