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

    Neuronpedia

    INDEX
    Explanations

    phrases related to follow-up actions and requests

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     tinte
    -0.65
     siff
    -0.63
     marte
    -0.60
     Cartes
    -0.57
     ordina
    -0.56
    litos
    -0.55
     Chapitre
    -0.54
     Ouv
    -0.54
     Cfr
    -0.54
     Garanti
    -0.53
    POSITIVE LOGITS
     followup
    0.95
     follow
    0.68
     impelled
    0.63
     vainly
    0.62
     unve
    0.62
     disambigu
    0.60
    follow
    0.59
     disagre
    0.58
     ujedno
    0.57
    glowing
    0.56
    Act Density 0.099%

    No Known Activations