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

    Neuronpedia

    INDEX
    Explanations

    instances of the pronoun "we"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.80
     fince
    -0.75
     Monfieur
    -0.74
     itſelf
    -0.74
     Thon
    -0.71
     Houſe
    -0.70
     Reſ
    -0.70
     Eſ
    -0.68
     whoſe
    -0.67
     Efq
    -0.67
    POSITIVE LOGITS
     we
    2.26
     they
    1.50
     he
    1.28
    we
    1.27
     you
    1.26
     I
    1.22
     she
    1.18
     our
    1.13
     THEY
    1.07
     We
    1.00
    Act Density 0.124%

    No Known Activations