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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "set" and its various forms, indicating a focus on the concept of establishing or arranging something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WARDS
    -0.20
    soever
    -0.18
    wards
    -0.17
    ULATE
    -0.17
    verty
    -0.17
    gether
    -0.16
    uter
    -0.16
    iku
    -0.15
    .liferay
    -0.15
    berman
    -0.15
    POSITIVE LOGITS
     sail
    0.26
     loose
    0.24
    embro
    0.22
     aside
    0.22
     apart
    0.21
     Sail
    0.20
     forth
    0.20
    zt
    0.20
     up
    0.19
     abl
    0.19
    Act Density 0.017%

    No Known Activations