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

    Neuronpedia

    INDEX
    Explanations

    references to friends and friendships

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

    friend and friends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XMLSchema
    -0.40
    厲害
    -0.38
    Autoritní
    -0.34
    ulism
    -0.33
    extAlignment
    -0.32
    GridLayout
    -0.32
    ühle
    -0.31
    inheritDoc
    -0.31
    厉害
    -0.30
     visant
    -0.30
    POSITIVE LOGITS
     friends
    1.82
     friend
    1.77
    friends
    1.63
    Friends
    1.60
    friend
    1.56
     Friend
    1.55
     Friends
    1.54
    Friend
    1.53
     FRIENDS
    1.51
     FRIEND
    1.43
    Act Density 0.060%

    No Known Activations