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

    Neuronpedia

    INDEX
    Explanations

    references to personal and social relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azer
    -0.15
    CompleteListener
    -0.14
    edo
    -0.14
    зÑı
    -0.14
    ansom
    -0.14
    atore
    -0.14
    åŁ
    -0.14
    ichni
    -0.13
    ville
    -0.13
    /Main
    -0.13
    POSITIVE LOGITS
     fellow
    0.92
     colleagues
    0.84
     colleague
    0.79
     peers
    0.74
     friends
    0.68
     teammate
    0.66
     classmates
    0.66
     friend
    0.63
     teammates
    0.61
     Fellow
    0.60
    Act Density 0.534%

    No Known Activations