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

    Neuronpedia

    INDEX
    Explanations

    names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iencies
    -0.65
    arial
    -0.62
    itaire
    -0.61
    drawn
    -0.61
    geries
    -0.60
     duplication
    -0.59
     parachute
    -0.59
    antine
    -0.58
    owship
    -0.57
    draft
    -0.57
    POSITIVE LOGITS
     replied
    1.28
    âĢ
    1.25
     (@
    1.19
     told
    1.15
     explained
    1.13
     said
    1.12
     exclaimed
    1.09
     tweeted
    1.09
     joked
    1.07
     remarked
    1.07
    Act Density 0.201%

    No Known Activations