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

    Neuronpedia

    INDEX
    Explanations

    references to friendships or personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.79
     cdti
    -0.75
     Anſ
    -0.74
     sandero
    -0.73
    baga
    -0.72
     ſever
    -0.70
    ))))))))
    -0.69
     myſelf
    -0.68
    Autoritní
    -0.68
    исленность
    -0.66
    POSITIVE LOGITS
     friend
    1.83
     friends
    1.82
    friend
    1.60
     Friends
    1.57
    friends
    1.57
     FRIEND
    1.56
     Friend
    1.56
    Friend
    1.53
     FRIENDS
    1.50
     friendship
    1.49
    Act Density 0.159%

    No Known Activations