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

    Neuronpedia

    INDEX
    Explanations

    phrases related to citations, quotes, and repeated phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.65
     accountId
    -0.65
     shewn
    -0.59
     resultList
    -0.59
     dimensionless
    -0.57
     loggedIn
    -0.55
     bituminous
    -0.55
     discontinuities
    -0.54
     diffusivity
    -0.53
     rtn
    -0.53
    POSITIVE LOGITS
     fantaisie
    0.78
     quoique
    0.70
     nôtre
    0.70
     rédig
    0.67
     fabriqué
    0.66
     plais
    0.64
     célé
    0.63
     prédé
    0.63
     RSSSF
    0.62
     confé
    0.61
    Act Density 0.404%

    No Known Activations