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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, potentially related to announcements or events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ann."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     liking
    -0.74
     glove
    -0.72
     Left
    -0.71
     intelligence
    -0.67
     wrong
    -0.66
     wing
    -0.64
     preference
    -0.64
     luggage
    -0.64
     leads
    -0.63
     improved
    -0.62
    POSITIVE LOGITS
    Ann
    3.86
    Anne
    1.82
    ann
    1.62
     ANN
    1.48
    ANN
    1.39
     Ann
    1.30
    Month
    1.22
    Marie
    1.19
    iann
    1.15
    Wan
    1.12
    Act Density 0.015%

    No Known Activations