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

    Neuronpedia

    INDEX
    Explanations

    references to different types of burgers

    oai_token-act-pair · gpt-3.5-turbo

    references to burgers and burger-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agall
    -0.87
    agnetic
    -0.77
    itored
    -0.76
    Downloadha
    -0.72
    audi
    -0.71
    etheless
    -0.70
    theless
    -0.70
    uchin
    -0.70
     Atmospheric
    -0.69
    itably
    -0.67
    POSITIVE LOGITS
     burger
    1.14
     fries
    1.12
     burgers
    1.07
    urger
    1.05
     joints
    1.00
     steak
    0.97
     Burger
    0.94
     hamb
    0.92
    meat
    0.90
    rito
    0.90
    Act Density 0.049%

    No Known Activations