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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical settings and specifications, such as FPS, IQ, SES, weight, albedo, and flux

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Darío
    -0.92
     Valentín
    -0.80
     Compañ
    -0.71
     Comandante
    -0.70
     Lázaro
    -0.70
     Belén
    -0.69
     Cæ
    -0.68
     Messieurs
    -0.68
     Alcalde
    -0.68
     Leopoldo
    -0.67
    POSITIVE LOGITS
     frumos
    0.66
     vla
    0.66
     zů
    0.66
     frumo
    0.65
     ușor
    0.64
     reduction
    0.62
     dintr
    0.59
     calculation
    0.58
    raught
    0.58
     reprez
    0.56
    Act Density 0.373%

    No Known Activations