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

    Neuronpedia

    INDEX
    Explanations

    expressions of promises and commitments made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allis
    -0.14
    osate
    -0.14
    671
    -0.14
    _dummy
    -0.14
    -menu
    -0.13
    erc
    -0.13
    /edit
    -0.13
    :::::::
    -0.13
    uate
    -0.13
     Sat
    -0.13
    POSITIVE LOGITS
     promises
    0.18
     promise
    0.17
     vow
    0.17
     Promise
    0.15
     vows
    0.14
    arih
    0.14
     unw
    0.14
     NOTIFY
    0.14
    ürn
    0.14
    promise
    0.14
    Act Density 0.120%

    No Known Activations