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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate recommendations and personal connections with family and friends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "friends" or "family"

    np_acts-logits-general · gemini-2.0-flash

    friends and family

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]));
    -0.53
     noastre
    -0.52
     القرن
    -0.48
     tayo
    -0.48
    +#+#
    -0.47
    seamnă
    -0.46
     copias
    -0.46
     provisoire
    -0.46
     Мексичка
    -0.45
    ()")
    -0.45
    POSITIVE LOGITS
     friends
    2.85
    friends
    2.32
     friend
    2.31
    Friends
    2.10
     Friends
    2.07
    friend
    1.99
     FRIENDS
    1.98
     relatives
    1.91
     vrienden
    1.88
     amigos
    1.84
    Act Density 0.476%

    No Known Activations