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

    Neuronpedia

    INDEX
    Explanations

    mentions of relationships or interactions between individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and focus on topics related to companionship and family dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    herer
    -0.78
    hazard
    -0.77
    ibaba
    -0.77
    cens
    -0.75
    pai
    -0.71
    Layer
    -0.71
    STD
    -0.70
    esthesia
    -0.70
    iversity
    -0.70
    peak
    -0.70
    POSITIVE LOGITS
     duo
    1.80
     pair
    1.72
     trio
    1.57
     twins
    1.50
     latter
    1.41
     couple
    1.40
     brothers
    1.30
     two
    1.21
     siblings
    1.21
     similarities
    1.20
    Act Density 0.310%

    No Known Activations