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

    Neuronpedia

    INDEX
    Explanations

    references to relationships or interactions with individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to companionship or partnership, particularly in terms of relationships or camaraderie

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icum
    -0.96
    acco
    -0.79
    inyl
    -0.77
    lander
    -0.77
    kefeller
    -0.75
    ights
    -0.75
    shire
    -0.75
    odd
    -0.73
    lich
    -0.72
    schild
    -0.68
    POSITIVE LOGITS
     Mate
    0.90
     mate
    0.84
     mates
    0.81
     versa
    0.73
    mates
    0.72
     Nieto
    0.68
    vich
    0.67
    mate
    0.67
     goodbye
    0.66
     Swap
    0.64
    Act Density 0.016%

    No Known Activations