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

    Neuronpedia

    INDEX
    Explanations

    instances of a specific character, particularly focusing on the letter "e"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portály
    -0.56
    PASSED
    -0.56
     EN
    -0.54
    ptonshire
    -0.54
     E
    -0.53
    úgó
    -0.53
    CodedInputStream
    -0.52
     EL
    -0.51
    memp
    -0.51
    auger
    -0.50
    POSITIVE LOGITS
    e
    3.45
    eer
    1.18
    eet
    1.16
    eit
    1.08
    ete
    1.06
    eis
    1.06
    a
    1.04
    ei
    1.03
    i
    1.03
    ee
    1.01
    Act Density 0.140%

    No Known Activations