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

    Neuronpedia

    INDEX
    Explanations

    references to specific organizations and their actions

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

    Prepositions/conjunctions followed by nouns/proper nouns

    np_acts-logits-general · gemini-2.0-flash

    specific titles and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cipar
    -0.54
    lossians
    -0.51
     Subpart
    -0.51
    hisattva
    -0.51
     surla
    -0.49
     Squadron
    -0.49
     Sélectionnez
    -0.48
     Descriptor
    -0.48
     Cohort
    -0.47
    Rptr
    -0.46
    POSITIVE LOGITS
     Food
    1.21
     Music
    1.06
     Energy
    1.04
     Oil
    1.03
     Coffee
    1.02
     Health
    1.01
     Wine
    1.01
     Gas
    1.00
     Water
    0.99
    Food
    0.99
    Act Density 0.630%

    No Known Activations