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

    Neuronpedia

    INDEX
    Explanations

    mentions of interpersonal interactions and relationships

    oai_token-act-pair · gpt-3.5-turbo

    themes of interpersonal relationships and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umes
    -0.73
     omission
    -0.65
     Prediction
    -0.61
    cens
    -0.60
     Detected
    -0.60
     Seller
    -0.59
     Baird
    -0.59
     Shap
    -0.59
     suppression
    -0.59
    anasia
    -0.59
    POSITIVE LOGITS
     exchanged
    1.27
     mutually
    1.23
     parted
    1.21
     bonded
    1.14
     reconcil
    1.11
     both
    1.09
     banter
    1.07
     discuss
    1.04
     spar
    1.03
    both
    1.02
    Act Density 0.297%

    No Known Activations