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

    Neuronpedia

    INDEX
    Explanations

    repeated vowel sounds or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.28
    ska
    -0.23
    cion
    -0.23
    eb
    -0.22
    path
    -0.21
    sburg
    -0.20
    si
    -0.19
    न
    -0.19
    cy
    -0.19
    care
    -0.19
    POSITIVE LOGITS
    z
    0.50
    e
    0.39
    es
    0.35
    i
    0.30
    zv
    0.29
    zf
    0.29
    zl
    0.28
    ëĬĶ
    0.28
    zem
    0.28
    zman
    0.27
    Act Density 0.209%

    No Known Activations