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

    Neuronpedia

    INDEX
    Explanations

    references to geographic locations and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wirkung
    -0.31
     للمعارف
    -0.30
     posibles
    -0.30
     করে
    -0.29
     spent
    -0.28
     siang
    -0.28
    不已
    -0.28
     lauk
    -0.28
     láser
    -0.27
     nearly
    -0.27
    POSITIVE LOGITS
    awtextra
    0.87
     noDo
    0.73
    EndProject
    0.64
    ніципалі
    0.64
     Taktlose
    0.63
    WithIOException
    0.63
    RTEX
    0.62
     ProtoMessage
    0.60
    Werdegang
    0.60
     виправивши
    0.59
    Act Density 0.702%

    No Known Activations