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

    Neuronpedia

    INDEX
    Explanations

    comparisons related to quantity or degree, specifically focusing on the concept of "less."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a reduction in quantity or cost

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DK
    -0.72
     Events
    -0.69
    âĹ¼
    -0.68
    Draft
    -0.66
     Advis
    -0.63
     Properties
    -0.62
    omnia
    -0.62
    de
    -0.62
    Spons
    -0.61
    SU
    -0.61
    POSITIVE LOGITS
     than
    1.12
    ened
    1.07
    ening
    0.96
     forgiving
    0.76
     glamorous
    0.70
    than
    0.68
     behaved
    0.68
     detectable
    0.67
     intrusive
    0.66
     conspicuous
    0.66
    Act Density 0.036%

    No Known Activations