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

    Neuronpedia

    INDEX
    Explanations

    mentions of different types of meat

    oai_token-act-pair · gpt-3.5-turbo

    references to meat and its consumption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Telecommunications
    -0.75
     Spac
    -0.64
     Morse
    -0.64
     Polaris
    -0.63
    ipolar
    -0.61
     Learned
    -0.61
     Fundamental
    -0.60
     Kard
    -0.60
    owered
    -0.59
     Bland
    -0.59
    POSITIVE LOGITS
    balls
    1.42
    lo
    1.07
    packing
    1.03
    heads
    1.02
    ball
    1.01
    meat
    1.00
     slic
    1.00
    pack
    0.97
    bone
    0.97
     pies
    0.96
    Act Density 0.049%

    No Known Activations