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

    Neuronpedia

    INDEX
    Explanations

    references to the word "us" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.95
     Houſe
    -0.87
     houſe
    -0.85
     pleaſure
    -0.83
     Charlemagne
    -0.81
     Efq
    -0.81
     purpoſe
    -0.80
     Karak
    -0.78
     Chy
    -0.77
     ſever
    -0.77
    POSITIVE LOGITS
     us
    1.51
     Us
    1.25
    Us
    1.08
     We
    1.04
     we
    0.92
    We
    0.85
     WE
    0.83
     them
    0.82
     me
    0.80
    us
    0.80
    Act Density 0.024%

    No Known Activations