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

    Neuronpedia

    INDEX
    Explanations

    food-related words and cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    food-related terminology and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    htaking
    -0.58
     virginity
    -0.57
     precisely
    -0.57
     NEVER
    -0.55
    osate
    -0.54
     hardly
    -0.52
    ãĥ¯ãĥ³
    -0.52
    0000000000000000
    -0.51
    DonaldTrump
    -0.51
     EVERY
    -0.50
    POSITIVE LOGITS
    cellaneous
    0.68
     other
    0.65
     others
    0.63
     afterward
    0.62
    Other
    0.59
     else
    0.57
    other
    0.56
    Later
    0.56
     Others
    0.55
     Other
    0.55
    Act Density 1.030%

    No Known Activations