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

    Neuronpedia

    INDEX
    Explanations

    expressions of desire or preference toward actions or objects

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

    desire or liking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.34
     poffible
    -0.30
     cris
    -0.30
     power
    -0.29
    ьажоргаш
    -0.29
    ientí
    -0.29
     wei
    -0.28
     Karo
    -0.28
     instin
    -0.28
     false
    -0.28
    POSITIVE LOGITS
     surla
    0.79
     gostaria
    0.69
     gustaría
    0.65
    aimerais
    0.57
    AddWithValue
    0.56
     quisiera
    0.50
    expandindo
    0.49
    jalá
    0.49
     EconPapers
    0.49
    وفاته
    0.48
    Act Density 0.055%

    No Known Activations