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

    Neuronpedia

    INDEX
    Explanations

    prepositions and relationships between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anza
    -0.16
    ateurs
    -0.15
     trú
    -0.15
    sett
    -0.15
    ankan
    -0.14
    tre
    -0.14
    munition
    -0.14
    ALCHEMY
    -0.14
    ansk
    -0.14
    erus
    -0.14
    POSITIVE LOGITS
    adians
    0.14
    icut
    0.14
    ian
    0.14
     Appropri
    0.14
     Chrom
    0.14
    ade
    0.14
    .si
    0.13
    ifer
    0.13
    xEB
    0.13
    Ñģок
    0.13
    Act Density 0.407%

    No Known Activations