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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter "e" in various forms, focusing particularly on its prominence in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    so
    -0.27
    nya
    -0.26
    ss
    -0.26
    na
    -0.25
    ness
    -0.25
    lo
    -0.23
    rie
    -0.21
    mi
    -0.21
    no
    -0.21
    nu
    -0.21
    POSITIVE LOGITS
    ylland
    0.18
    ulers
    0.17
    postalcode
    0.17
    yro
    0.16
    eft
    0.16
    iou
    0.15
    eview
    0.15
    yd
    0.15
    eo
    0.15
    iš
    0.15
    Act Density 0.102%

    No Known Activations