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

    Neuronpedia

    INDEX
    Explanations

    words with the suffix 'ine', indicating a focus on chemical compounds or specific named entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wy
    -0.22
    èķ
    -0.17
    wort
    -0.17
    Keeper
    -0.17
    winner
    -0.16
    worthy
    -0.16
    mitted
    -0.16
    PERT
    -0.15
    wyn
    -0.15
    roj
    -0.15
    POSITIVE LOGITS
    jad
    0.24
    arity
    0.23
    ering
    0.23
    yen
    0.18
    yards
    0.18
    ine
    0.17
    au
    0.17
    iros
    0.16
    ære
    0.16
    ira
    0.15
    Act Density 0.037%

    No Known Activations