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

    Neuronpedia

    INDEX
    Explanations

    references to fellow individuals or groups in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stiles
    -0.64
    sierung
    -0.59
    vernight
    -0.57
     pido
    -0.55
    brett
    -0.55
     Nieuws
    -0.55
     Carboniferous
    -0.55
    <?>>
    -0.55
    ATTN
    -0.55
     Sands
    -0.54
    POSITIVE LOGITS
     colleague
    1.35
     colleagues
    1.28
     peers
    1.07
     classmate
    1.06
     fellow
    1.04
     colega
    1.03
     FELLOW
    1.02
     classmates
    1.02
     Colleagues
    1.00
     colegas
    0.95
    Act Density 0.135%

    No Known Activations