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

    Neuronpedia

    INDEX
    Explanations

    references to body weight and fat content

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "fat" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rowling
    -0.74
     Aerospace
    -0.73
    ULT
    -0.73
    ECH
    -0.72
     Ascend
    -0.71
    yrinth
    -0.69
     Doct
    -0.69
     Remastered
    -0.69
    UAL
    -0.67
     McKenna
    -0.66
    POSITIVE LOGITS
    igue
    1.16
    rition
    1.03
    wallet
    0.95
    hered
    0.93
    fat
    0.92
    bike
    0.89
    tailed
    0.88
    ishes
    0.86
    bag
    0.84
    allo
    0.80
    Act Density 0.012%

    No Known Activations