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

    Neuronpedia

    INDEX
    Explanations

    references to friends and social relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Leer
    -0.31
     Policy
    -0.29
     createSlice
    -0.29
     Leona
    -0.29
     continu
    -0.29
     Warrior
    -0.28
    LastError
    -0.28
     Vision
    -0.28
     Leer
    -0.28
     vision
    -0.28
    POSITIVE LOGITS
     friends
    0.80
    friends
    0.76
     friend
    0.72
    friend
    0.72
    Friends
    0.70
     acquaintances
    0.69
     незавершена
    0.68
     vrienden
    0.68
     FRIENDS
    0.68
     Freundin
    0.66
    Act Density 0.422%

    No Known Activations