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

    Neuronpedia

    INDEX
    Explanations

    references to protocols in various contexts

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

    study protocols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cinquante
    -0.48
     franceses
    -0.45
     bénéfice
    -0.43
     étrangère
    -0.42
     pensent
    -0.41
     femininas
    -0.40
     financière
    -0.40
     alemanes
    -0.40
     francesa
    -0.40
     féminine
    -0.39
    POSITIVE LOGITS
     protocol
    2.20
     protocols
    2.11
     Protocol
    2.06
     PROTOCOL
    2.03
     Protocols
    1.95
    Protocol
    1.85
    protocol
    1.84
    protocols
    1.74
    PROTOCOL
    1.68
    Protocols
    1.66
    Act Density 0.009%

    No Known Activations