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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives indicating a higher degree of a quality

    oai_token-act-pair · gpt-3.5-turbo

    comparative adjectives and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pta
    -0.69
    ILLE
    -0.67
    ainted
    -0.66
    EP
    -0.66
     Clerk
    -0.64
     Dresden
    -0.64
     absence
    -0.61
    ela
    -0.61
    WAR
    -0.61
    vez
    -0.60
    POSITIVE LOGITS
     than
    1.32
    than
    1.20
     Than
    1.18
    iating
    0.85
    iable
    0.77
     manageable
    0.73
    idge
    0.73
    é¾įå¥ij士
    0.71
    omas
    0.70
     ado
    0.69
    Act Density 0.082%

    No Known Activations