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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "engage" and its variants, indicating a focus on involvement and participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swire
    -0.18
    ãģŀ
    -0.15
    ided
    -0.15
    ÏĨÏħ
    -0.15
    -ÑĤо
    -0.15
    omial
    -0.15
    ÃŃr
    -0.15
    acular
    -0.15
    idlo
    -0.14
    celed
    -0.14
    POSITIVE LOGITS
    ment
    0.23
    ging
    0.21
    ments
    0.20
    /dis
    0.20
    ement
    0.17
    ged
    0.17
    forth
    0.16
    ful
    0.16
    ering
    0.16
     directly
    0.16
    Act Density 0.022%

    No Known Activations