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

    Neuronpedia

    INDEX
    Explanations

    expressions of happiness and gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æŀļ
    -0.17
    linkplain
    -0.15
     Mafia
    -0.14
    amac
    -0.14
    bage
    -0.14
    udi
    -0.14
    çħ
    -0.14
    Ñı
    -0.13
    .extract
    -0.13
    pcs
    -0.13
    POSITIVE LOGITS
     finally
    0.20
    finally
    0.18
    å¦ĤæѤ
    0.18
    è¿Ļä¹Ī
    0.17
    atile
    0.16
    ÙģاÙĤ
    0.15
    andin
    0.15
     Bott
    0.14
    frey
    0.14
     cljs
    0.14
    Act Density 0.166%

    No Known Activations