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

    Neuronpedia

    INDEX
    Explanations

    the word "so" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.82
     Cæsar
    -0.79
    μία
    -0.78
     Breton
    -0.76
    Portail
    -0.74
     vertes
    -0.73
    ſelf
    -0.72
     Cey
    -0.71
     Artemis
    -0.70
     Pernambuco
    -0.70
    POSITIVE LOGITS
     so
    2.52
     So
    2.15
    So
    2.10
    so
    2.03
     SO
    1.80
    SO
    1.47
     sooooo
    1.32
    Sooo
    1.32
     sooo
    1.32
     soooo
    1.26
    Act Density 0.117%

    No Known Activations