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

    Neuronpedia

    INDEX
    Explanations

    references to financial deficiencies or budget deficits

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

    deficit and deficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     way
    -0.55
     “
    -0.54
    Way
    -0.52
     Way
    -0.52
    Woman
    -0.50
     rubber
    -0.49
    World
    -0.49
     WAYS
    -0.48
    “
    -0.47
    Words
    -0.46
    POSITIVE LOGITS
     Deficit
    1.04
     deficit
    1.02
    ficit
    0.99
     deficits
    0.85
    icit
    0.75
     Defic
    0.74
     déficit
    0.70
     deficiencies
    0.63
     deficiency
    0.61
    igent
    0.61
    Act Density 0.008%

    No Known Activations