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

    Neuronpedia

    INDEX
    Explanations

    terms related to friendship and social connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baga
    -0.92
    oriasis
    -0.87
     Theaters
    -0.81
    zugehen
    -0.80
    jména
    -0.77
     cappello
    -0.77
     بيها
    -0.77
     silenzio
    -0.76
     Hv
    -0.76
     cielos
    -0.75
    POSITIVE LOGITS
     friends
    1.61
     Friends
    1.55
    friends
    1.47
     FRIENDS
    1.43
    Friends
    1.36
     friend
    1.33
     Friend
    1.32
     FRIEND
    1.28
    Friend
    1.21
     Friendship
    1.20
    Act Density 0.067%

    No Known Activations