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

    Neuronpedia

    INDEX
    Explanations

    words associated with social activities or communal aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensex
    -0.21
    ÃŃvel
    -0.16
    ooled
    -0.15
    usk
    -0.15
    sep
    -0.15
    éĿĴ
    -0.15
    ób
    -0.15
    út
    -0.14
    .ActionListener
    -0.14
    iris
    -0.14
    POSITIVE LOGITS
    chie
    0.24
    ied
    0.24
    child
    0.23
    itz
    0.22
    atz
    0.21
    icht
    0.21
    cha
    0.19
    ula
    0.19
    etz
    0.18
    auty
    0.18
    Act Density 0.021%

    No Known Activations