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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships between individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edla
    -0.17
    PLEASE
    -0.16
    olina
    -0.15
    udeau
    -0.14
     Feder
    -0.14
    :animated
    -0.14
    iedo
    -0.13
    embr
    -0.13
    bih
    -0.13
    _LVL
    -0.13
    POSITIVE LOGITS
     friendship
    0.36
     friendships
    0.34
     Friendship
    0.27
    friend
    0.25
     friend
    0.25
     FRIEND
    0.24
    Friend
    0.23
     Friend
    0.22
     friends
    0.22
     Freund
    0.20
    Act Density 0.145%

    No Known Activations