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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and thankfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eca
    -0.16
    elho
    -0.14
    aná
    -0.14
    /pages
    -0.14
    antro
    -0.14
    edback
    -0.14
    à¥įवत
    -0.14
     اختÛĮار
    -0.14
    omm
    -0.14
    an
    -0.13
    POSITIVE LOGITS
    sgiving
    0.21
    fulness
    0.20
    ness
    0.17
    esson
    0.15
    atra
    0.15
    kp
    0.15
    fully
    0.15
    ilty
    0.15
    utor
    0.15
    sembler
    0.14
    Act Density 0.024%

    No Known Activations