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 different attributes or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Telecommunications
    -0.76
     Learned
    -0.71
     Citizens
    -0.71
     Universal
    -0.63
     Morse
    -0.61
     Bland
    -0.60
     Telecom
    -0.60
     Electronic
    -0.60
     runaway
    -0.60
     bluff
    -0.58
    POSITIVE LOGITS
    balls
    1.39
    lo
    1.19
    packing
    1.13
    cake
    1.09
    meat
    0.99
    ball
    0.97
     pies
    0.94
    aceous
    0.93
     broth
    0.93
    bags
    0.92
    Act Density 0.051%

    No Known Activations