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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "en."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swagen
    -0.17
    ocaust
    -0.16
    triangle
    -0.15
    erne
    -0.15
    ĥ½
    -0.15
    car
    -0.14
    ocular
    -0.14
    istrovstvÃŃ
    -0.14
    skyt
    -0.14
    ãģĹãĤĩ
    -0.14
    POSITIVE LOGITS
    rich
    0.16
    rst
    0.15
    ospace
    0.15
    ongan
    0.15
    رش
    0.15
     WHETHER
    0.15
    oders
    0.14
    uste
    0.14
    775
    0.14
    nob
    0.14
    Act Density 0.040%

    No Known Activations