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

    Neuronpedia

    INDEX
    Explanations

    instances of specific suffixes or endings in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tot
    -0.18
    Ñı
    -0.17
    tel
    -0.16
    ept
    -0.16
    orld
    -0.16
    éro
    -0.16
    tep
    -0.16
    tega
    -0.16
    letcher
    -0.16
    SSION
    -0.15
    POSITIVE LOGITS
    ey
    0.19
    presso
    0.18
    oteric
    0.17
    ophage
    0.17
    itated
    0.17
    itating
    0.17
    apeake
    0.17
    pecially
    0.17
    ellschaft
    0.16
    eker
    0.16
    Act Density 0.032%

    No Known Activations