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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an understatement

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey degrees of understatement or express opinions about something being described

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     coerc
    -0.75
    nels
    -0.71
     interven
    -0.69
    doors
    -0.67
     Procedures
    -0.61
    iste
    -0.60
     harms
    -0.59
    ictive
    -0.58
    hooting
    -0.57
     ens
    -0.57
    POSITIVE LOGITS
     understatement
    1.10
     recalling
    0.88
     hindsight
    0.87
     recall
    0.87
     recol
    0.85
     credit
    0.85
     recollection
    0.84
     reminis
    0.84
     compare
    0.83
     remem
    0.82
    Act Density 0.434%

    No Known Activations