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

    Neuronpedia

    INDEX
    Explanations

    phrases related to diminishing or reducing something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sén
    -0.83
     Docteur
    -0.78
     unspeak
    -0.76
     Jusqu
    -0.74
     Autre
    -0.72
     Cinéma
    -0.71
     Rois
    -0.71
     Président
    -0.71
     Secrétaire
    -0.69
     Chapitre
    -0.69
    POSITIVE LOGITS
     less
    0.93
     LESS
    0.86
     Less
    0.82
    Less
    0.81
    less
    0.75
     menos
    0.71
     weniger
    0.71
    LESS
    0.70
     than
    0.66
     meno
    0.64
    Act Density 0.103%

    No Known Activations