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

    Neuronpedia

    INDEX
    Explanations

    words related to giving or receiving favor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    acts of kindness and support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nicamente
    -0.44
     viable
    -0.40
    quilo
    -0.39
     billeder
    -0.39
    wikkeld
    -0.39
     dourada
    -0.38
    nica
    -0.38
    ciato
    -0.38
    Embeddable
    -0.37
     dourado
    -0.37
    POSITIVE LOGITS
     favor
    1.32
    favor
    1.23
     favour
    1.16
     favors
    1.12
     favours
    1.06
    Favor
    1.05
     FAVOR
    1.04
     Favor
    1.04
     faveur
    0.83
     Fav
    0.81
    Act Density 0.008%

    No Known Activations