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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating quality or condition related to "well."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izzo
    -0.16
    887
    -0.15
    ean
    -0.15
    fty
    -0.15
    latlong
    -0.14
    elles
    -0.14
    alles
    -0.14
    stru
    -0.14
    linkplain
    -0.14
    ised
    -0.14
    POSITIVE LOGITS
    spring
    0.19
    akit
    0.17
    pj
    0.16
     well
    0.16
    ness
    0.15
    ington
    0.15
    peater
    0.14
    못
    0.14
    opi
    0.13
    inder
    0.13
    Act Density 0.035%

    No Known Activations