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

    Neuronpedia

    INDEX
    Explanations

    references to incentives and motivations related to actions and behaviors

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

    motivations or reasons

    np_acts-logits-general · gemini-2.0-flash

    reasons for actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    createCanvas
    -0.69
     Wikimedijinoj
    -0.66
     fråga
    -0.58
     betweenstory
    -0.56
     originaux
    -0.54
     recommandée
    -0.51
    leşti
    -0.51
    ppure
    -0.51
     fieldNum
    -0.50
     originale
    -0.48
    POSITIVE LOGITS
     motive
    0.90
     incentive
    0.85
     motivation
    0.80
     desire
    0.79
     incentives
    0.78
     motivated
    0.78
     want
    0.78
     eager
    0.77
     vested
    0.77
     willing
    0.74
    Act Density 0.451%

    No Known Activations