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

    Neuronpedia

    INDEX
    Explanations

    phrases that express gratitude or acknowledge contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antro
    -0.20
    echo
    -0.15
    .scalablytyped
    -0.15
    íĥĢ
    -0.15
    ondo
    -0.15
    ntl
    -0.14
    IDX
    -0.14
    ëªħ
    -0.14
    ubbo
    -0.13
    баÑĩ
    -0.13
    POSITIVE LOGITS
     gravity
    0.17
     thanks
    0.16
    ably
    0.15
     courtesy
    0.15
    verse
    0.14
    uating
    0.14
    istle
    0.14
     Prescott
    0.14
    -vis
    0.14
    elves
    0.14
    Act Density 0.016%

    No Known Activations