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

    Neuronpedia

    INDEX
    Explanations

    repeated use of the first-person pronoun "I."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.17
     Beſ
    -1.06
     Efq
    -1.05
     Reſ
    -1.03
     Monfieur
    -1.00
     Eſ
    -0.98
     Anſ
    -0.96
     Houſe
    -0.96
     ―――――
    -0.95
     ſeveral
    -0.93
    POSITIVE LOGITS
     I
    2.90
    I
    2.13
     we
    1.43
     i
    1.38
     We
    1.38
     my
    1.32
     я
    1.28
     My
    1.28
    我
    1.26
    We
    1.21
    Act Density 0.243%

    No Known Activations