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

    Neuronpedia

    INDEX
    Explanations

    information related to research projects and reports, especially focusing on findings and researchers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     velours
    -0.67
     Faculté
    -0.54
     pittores
    -0.54
     Gallimard
    -0.54
    箕
    -0.53
     Compt
    -0.53
     dynamis
    -0.52
     Foire
    -0.51
     impon
    -0.51
     fré
    -0.50
    POSITIVE LOGITS
     research
    1.29
    research
    1.17
     Research
    1.16
    Research
    1.14
     RESEARCH
    1.09
    RESEARCH
    1.04
     researches
    1.02
     researchers
    0.96
     researched
    0.91
     researcher
    0.91
    Act Density 0.099%

    No Known Activations