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

    Neuronpedia

    INDEX
    Explanations

    references to glass containers or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stery
    -0.17
    sts
    -0.17
    ertools
    -0.17
    eva
    -0.17
    memberof
    -0.15
    akeup
    -0.15
    tk
    -0.15
     glass
    -0.15
    deaux
    -0.15
    orsi
    -0.15
    POSITIVE LOGITS
    ware
    0.33
    gow
    0.30
    y
    0.28
    ses
    0.27
    (es
    0.26
    ed
    0.25
    ine
    0.24
    wort
    0.24
    house
    0.23
    work
    0.23
    Act Density 0.010%

    No Known Activations