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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate actions done to subjects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gave
    -0.62
     silencio
    -0.61
    DockStyle
    -0.61
    did
    -0.61
     cavallo
    -0.61
     Stä
    -0.60
    rý
    -0.59
     Gegenteil
    -0.59
     nélk
    -0.58
     did
    -0.58
    POSITIVE LOGITS
     flown
    1.78
     grown
    1.60
     spoken
    1.60
     blown
    1.55
     taken
    1.51
     risen
    1.51
     worn
    1.47
     fallen
    1.45
    taken
    1.40
     drawn
    1.40
    Act Density 0.132%

    No Known Activations