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

    Neuronpedia

    INDEX
    Explanations

    cheese-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of cheese

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nant
    -0.91
    igious
    -0.72
     eminent
    -0.69
    NEY
    -0.66
     Chatt
    -0.65
     Walton
    -0.63
    ounces
    -0.61
     Brow
    -0.60
    OR
    -0.60
    igators
    -0.60
    POSITIVE LOGITS
    cloth
    1.14
     cheese
    1.04
    weed
    0.94
    bowl
    0.93
    fruit
    0.91
     Cheese
    0.91
     popcorn
    0.90
     slic
    0.89
    ecake
    0.88
     sandwich
    0.87
    Act Density 0.010%

    No Known Activations