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

    Neuronpedia

    INDEX
    Explanations

    references to friendships and social connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baga
    -0.96
    oriasis
    -0.87
     Theaters
    -0.81
    jména
    -0.80
     Hv
    -0.77
    zugehen
    -0.77
    shtml
    -0.77
    paravant
    -0.76
     cappello
    -0.76
     cielos
    -0.75
    POSITIVE LOGITS
     friends
    1.76
     Friends
    1.71
     FRIENDS
    1.56
    friends
    1.56
    Friends
    1.51
     friend
    1.47
     Friend
    1.46
     FRIEND
    1.40
    Friend
    1.33
     Friendship
    1.28
    Act Density 0.049%

    No Known Activations