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
     Achtung
    -0.72
    μία
    -0.71
     hond
    -0.67
     Catania
    -0.66
     wur
    -0.65
     Breton
    -0.65
     vertes
    -0.65
    Keith
    -0.64
    indépendance
    -0.63
     Keith
    -0.62
    POSITIVE LOGITS
     so
    1.49
     So
    1.41
    So
    1.37
     SO
    1.29
    so
    1.24
    Sooo
    1.15
     Så
    1.14
     sooo
    1.03
     sooooo
    1.02
    SO
    1.01
    Act Density 0.101%

    No Known Activations