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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "so" at the beginning of sentences or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.17
     Anſ
    -1.04
     Reſ
    -1.01
     Cæsar
    -0.98
     itſelf
    -0.95
     myſelf
    -0.95
     Theſe
    -0.94
     Inſ
    -0.94
    ſelves
    -0.92
     Majefty
    -0.92
    POSITIVE LOGITS
     so
    4.23
    so
    3.10
     So
    2.88
    So
    2.80
     SO
    2.35
     så
    2.22
     так
    1.88
     sooooo
    1.88
     sooo
    1.87
    SO
    1.86
    Act Density 0.133%

    No Known Activations