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

    Neuronpedia

    INDEX
    Explanations

    references to commitments or pledges, particularly those related to oaths and promises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Italijanski
    -0.69
    EndTag
    -0.62
    цездатний
    -0.59
     Erişim
    -0.52
     thụ
    -0.50
    ischem
    -0.48
    ouwd
    -0.48
     disambiguazione
    -0.48
    ilación
    -0.47
    writeFieldEnd
    -0.47
    POSITIVE LOGITS
     promise
    1.76
     Promise
    1.75
    Promise
    1.61
     pledge
    1.61
     promised
    1.57
     promises
    1.56
     pledged
    1.55
    promise
    1.51
     pledges
    1.50
     pledging
    1.48
    Act Density 0.382%

    No Known Activations