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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "agreement" in various forms

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

    agreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fifth
    -0.53
    depuis
    -0.50
     Fifth
    -0.49
    Haute
    -0.48
    omitempty
    -0.47
    Océ
    -0.46
     castor
    -0.46
    Mauri
    -0.46
    sys
    -0.45
     thinks
    -0.45
    POSITIVE LOGITS
     agreement
    2.03
     Agreement
    1.97
    Agreement
    1.79
    agreement
    1.76
     Agreements
    1.70
     AGREEMENT
    1.66
     agreements
    1.62
     accordo
    1.13
    Agre
    1.08
     Vereinbarung
    1.08
    Act Density 0.011%

    No Known Activations