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

    Neuronpedia

    INDEX
    Explanations

    mentions of professional relationships with peers

    oai_token-act-pair · gpt-3.5-turbo

    references to colleagues in a professional or work-related context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Control
    -0.58
    archs
    -0.58
    vable
    -0.58
     streets
    -0.57
     hills
    -0.57
    dark
    -0.56
     islands
    -0.56
    oo
    -0.56
    ãĥİ
    -0.56
    acion
    -0.56
    POSITIVE LOGITS
     colleague
    3.83
     colleagues
    2.59
     classmate
    2.07
     comrade
    1.99
     teammate
    1.97
     cowork
    1.97
     collaborator
    1.90
     coworkers
    1.70
     friend
    1.66
     partner
    1.52
    Act Density 0.016%

    No Known Activations