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

    Neuronpedia

    INDEX
    Explanations

    phrases related to promises and commitments

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

    "promise" or its variations

    np_acts-logits-general · gemini-2.0-flash

    making promises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     view
    -0.35
     in
    -0.34
    UserType
    -0.32
     In
    -0.32
    -0.32
     Col
    -0.32
    userType
    -0.32
     Abteilung
    -0.32
     Utilizamos
    -0.31
     at
    -0.31
    POSITIVE LOGITS
     promise
    1.46
     Promise
    1.32
    promise
    1.30
    Promise
    1.24
     promises
    1.23
     promessa
    1.19
     promesa
    1.17
     promised
    1.17
     Promises
    1.09
     promesse
    1.06
    Act Density 0.099%

    No Known Activations