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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to social interaction among individuals in a group

    oai_token-act-pair · gpt-3.5-turbo

    references to peer relationships and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertility
    -0.64
    othe
    -0.64
    arm
    -0.61
     Liberties
    -0.59
    ohyd
    -0.59
    obiles
    -0.58
    effective
    -0.58
     Manufact
    -0.58
    ono
    -0.57
     Rouge
    -0.57
    POSITIVE LOGITS
     peers
    1.50
     classmates
    0.85
     peer
    0.83
    peer
    0.81
     contemporaries
    0.78
     siblings
    0.76
    Reviewed
    0.76
    flix
    0.74
     Cosponsors
    0.74
    ometimes
    0.74
    Act Density 0.007%

    No Known Activations