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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of 'way' or methods in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Silent
    -0.61
     phúc
    -0.59
    Silent
    -0.58
     Balboa
    -0.54
     Symbolic
    -0.53
     Perugia
    -0.52
    pflanzen
    -0.50
     kock
    -0.50
     Συ
    -0.50
     papilla
    -0.49
    POSITIVE LOGITS
     how
    1.20
     HOW
    0.94
     propOrder
    0.93
     ahogy
    0.93
    awtextra
    0.90
     way
    0.87
     hvordan
    0.83
    How
    0.81
     How
    0.81
     cómo
    0.80
    Act Density 0.094%

    No Known Activations