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

    Neuronpedia

    INDEX
    Explanations

    expressions of reverence and gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    resh
    -0.16
    373
    -0.14
    usted
    -0.14
    oy
    -0.14
    ayas
    -0.14
    oidal
    -0.14
    CKET
    -0.14
    bbe
    -0.13
    ness
    -0.13
    /e
    -0.13
    POSITIVE LOGITS
    -worthy
    0.25
    atory
    0.25
    ably
    0.24
    worthy
    0.23
    ingly
    0.17
    -paying
    0.17
     fallen
    0.16
    ovol
    0.15
    fully
    0.15
    ific
    0.15
    Act Density 0.087%

    No Known Activations