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

    Neuronpedia

    INDEX
    Explanations

    information related to people's physical attributes, specifically weight measurements

    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
    istically
    -0.79
    eer
    -0.77
    actionDate
    -0.77
    vironment
    -0.75
    onymous
    -0.74
    istic
    -0.74
    eday
    -0.72
    onyms
    -0.71
    opol
    -0.70
    ezvous
    -0.69
    POSITIVE LOGITS
     sterling
    1.12
     pounds
    0.99
     heavier
    0.93
    lbs
    0.91
     lbs
    0.91
     sacks
    0.86
     gorilla
    0.85
    Weight
    0.84
     weight
    0.81
     overweight
    0.79
    Act Density 0.015%

    No Known Activations