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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing the quality or desirability of items

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that express quality or desirability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lees
    -0.93
    ometers
    -0.88
    steps
    -0.88
    ernels
    -0.86
    aucuses
    -0.84
    hops
    -0.82
    tests
    -0.79
    ships
    -0.79
    levels
    -0.78
    events
    -0.78
    POSITIVE LOGITS
     piece
    1.21
     chunk
    1.07
     person
    0.99
     sized
    0.98
     paycheck
    0.98
     dose
    0.96
     meal
    0.96
     pair
    0.94
     slice
    0.92
     adversary
    0.91
    Act Density 0.403%

    No Known Activations