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

    Neuronpedia

    INDEX
    Explanations

    terms related to friendship and community

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

    amicus and friend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Inſ
    -0.43
    `]
    -0.42
    Życiorys
    -0.41
     hâte
    -0.41
    NSUInteger
    -0.39
    荸
    -0.39
    leſs
    -0.39
     itſelf
    -0.37
    ************/
    -0.37
     Jefus
    -0.37
    POSITIVE LOGITS
    FRIEND
    1.19
     FRIEND
    1.17
    friend
    1.09
     friendly
    1.09
     friendliness
    1.05
     Friendly
    1.04
     Friend
    1.02
     friend
    1.02
    Friend
    1.02
     unfriendly
    1.01
    Act Density 0.023%

    No Known Activations