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

    Neuronpedia

    INDEX
    Explanations

    information related to physical measurements such as weight

    oai_token-act-pair · gpt-3.5-turbo

    references to weight measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inel
    -0.75
    onyms
    -0.75
    istically
    -0.75
    opol
    -0.74
    onym
    -0.74
    onymous
    -0.73
    actionDate
    -0.73
    eer
    -0.72
    cki
    -0.68
     Emin
    -0.68
    POSITIVE LOGITS
     sterling
    1.20
     pounds
    1.00
     heavier
    0.94
     lbs
    0.93
    lbs
    0.90
     gorilla
    0.88
     weight
    0.84
     apiece
    0.83
     sacks
    0.83
    pound
    0.81
    Act Density 0.014%

    No Known Activations