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

    Neuronpedia

    INDEX
    Explanations

    references to close friendships and social connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Fellow
    -0.73
    fellow
    -0.61
     Fellow
    -0.60
     FELLOW
    -0.60
     teammate
    -0.57
     propOrder
    -0.55
     predecessor
    -0.55
    parsedMessage
    -0.54
    Rüyada
    -0.54
    Partner
    -0.52
    POSITIVE LOGITS
     friends
    1.41
     friend
    1.18
     Friends
    1.05
    friends
    1.03
    Friends
    0.97
     vrienden
    0.91
     FRIENDS
    0.91
     Freunde
    0.90
     fri
    0.88
    friend
    0.87
    Act Density 0.232%

    No Known Activations