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" and its variations

    np_acts-logits-general · gemini-2.0-flash

    future commitments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    makedirs
    -0.65
    fjspx
    -0.65
     Hayek
    -0.63
    textbackslash
    -0.63
    évaluateur
    -0.61
    documentclass
    -0.59
     Bourgoin
    -0.58
     endblock
    -0.58
    etcode
    -0.57
    PyTuple
    -0.56
    POSITIVE LOGITS
     promise
    1.24
     Promise
    1.24
     Promises
    1.17
    Promise
    1.17
     promises
    1.17
    Promises
    1.14
    promise
    1.14
     Promised
    1.00
     promised
    1.00
     promete
    0.97
    Act Density 0.086%

    No Known Activations