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

    Neuronpedia

    INDEX
    Explanations

    positive sentiments and affirmations in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.72
     noDo
    -0.60
     disambiguazione
    -0.57
     linkovi
    -0.55
    httphttps
    -0.50
    enterOuterAlt
    -0.48
     estekak
    -0.48
     utafitiHapana
    -0.48
    NameInMap
    -0.45
    Lähteet
    -0.44
    POSITIVE LOGITS
     Normdatei
    0.51
     كومونز
    0.48
    msgTypes
    0.47
    ViewFeatures
    0.46
     trotzdem
    0.43
    Nevertheless
    0.43
     nonetheless
    0.42
     Nonetheless
    0.42
    不然
    0.41
     Nevertheless
    0.41
    Act Density 0.457%

    No Known Activations