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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter 'e' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    e
    -0.36
    z
    -0.35
    y
    -0.33
    ãģŁ
    -0.33
    p
    -0.32
    k
    -0.30
    ãģ¦
    -0.30
    f
    -0.28
    q
    -0.28
    c
    -0.28
    POSITIVE LOGITS
    legant
    0.19
    vidence
    0.19
    lev
    0.19
    conom
    0.19
    clipse
    0.18
    lected
    0.18
    agle
    0.18
    vo
    0.18
    levation
    0.18
    levator
    0.18
    Act Density 0.037%

    No Known Activations