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

    Neuronpedia

    INDEX
    Explanations

    comparative expressions indicating an improvement or a preference

    oai_token-act-pair · gpt-3.5-turbo

    comparisons emphasizing improvement or superiority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lees
    -1.07
    coins
    -0.96
    events
    -0.88
    ulations
    -0.83
    casts
    -0.83
    guards
    -0.80
    bows
    -0.79
    ships
    -0.79
     Committees
    -0.77
    marks
    -0.77
    POSITIVE LOGITS
     version
    1.17
     option
    1.00
     solution
    0.96
     thing
    0.94
     explanation
    0.94
     approximation
    0.91
     way
    0.89
     dimension
    0.89
     timetable
    0.88
     standpoint
    0.88
    Act Density 0.099%

    No Known Activations