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

    Neuronpedia

    INDEX
    Explanations

    references to bullying and social dynamics among students

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ansatte
    -0.76
     suaminya
    -0.75
     dipendenti
    -0.61
    Husband
    -0.59
     suami
    -0.58
     مفص
    -0.57
    ParallelGroup
    -0.57
     réfugiés
    -0.56
    extAlignment
    -0.56
     istrinya
    -0.56
    POSITIVE LOGITS
     girlfriends
    0.78
     frat
    0.73
     buddies
    0.68
     peers
    0.68
     girls
    0.66
     gangs
    0.66
     mates
    0.65
     classmates
    0.64
     peer
    0.64
     Peer
    0.64
    Act Density 0.316%

    No Known Activations