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

    Neuronpedia

    INDEX
    Explanations

    references to rivers and their geographical attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     leksikon
    -0.55
     defaultstate
    -0.52
    ❉
    -0.49
    rój
    -0.47
     StatefulWidget
    -0.47
     arran
    -0.46
    diocese
    -0.46
     Hiller
    -0.46
    ритори
    -0.46
     indé
    -0.46
    POSITIVE LOGITS
     rivers
    0.91
     river
    0.89
     streams
    0.85
     tributaries
    0.83
     River
    0.82
     fiume
    0.77
     rivière
    0.75
     flows
    0.74
     flow
    0.74
     Streams
    0.73
    Act Density 0.115%

    No Known Activations