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

    Neuronpedia

    INDEX
    Explanations

    words and phrases expressing varying levels of interest or concern

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

    subject of interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elettrica
    -0.30
     najbol
    -0.28
    Atsauces
    -0.28
    dowa
    -0.28
    SBATCH
    -0.27
     CURIAM
    -0.26
     épreuves
    -0.26
     Verfügung
    -0.26
    ục
    -0.26
     Ağ
    -0.25
    POSITIVE LOGITS
     interest
    1.12
    interest
    1.07
     interested
    1.05
    interested
    1.04
     Interest
    1.04
    Interest
    1.02
     INTEREST
    0.99
    INTEREST
    0.96
     interes
    0.96
     Interested
    0.96
    Act Density 0.232%

    No Known Activations