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

    Neuronpedia

    INDEX
    Explanations

    plural forms of nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ship
    -0.27
    ships
    -0.25
    shire
    -0.24
    sWith
    -0.23
    sk
    -0.22
    side
    -0.22
    ski
    -0.21
    sson
    -0.20
    site
    -0.20
    soever
    -0.20
    POSITIVE LOGITS
    ee
    0.28
    ey
    0.26
    presso
    0.25
    ek
    0.25
    apeake
    0.25
    cence
    0.23
    earch
    0.22
    pecially
    0.22
    eee
    0.21
    prit
    0.21
    Act Density 0.087%

    No Known Activations