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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotion and personal sentiments in letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odash
    -0.16
     normally
    -0.16
    ê°ij
    -0.15
    IClient
    -0.15
    pter
    -0.14
    normally
    -0.14
    errick
    -0.14
    emmel
    -0.14
     obviously
    -0.14
    Å¡ka
    -0.14
    POSITIVE LOGITS
     &
    0.21
     Colo
    0.20
     &↵
    0.19
    âŁ
    0.19
    [o
    0.19
     agre
    0.18
     (&
    0.17
     acct
    0.16
     Gen
    0.16
    [:]
    0.15
    Act Density 0.023%

    No Known Activations