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

    Neuronpedia

    INDEX
    Explanations

    structured data entries like document IDs, titles, descriptions, and user information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     kristal
    -0.73
     lü
    -0.68
     Demok
    -0.68
     konserv
    -0.66
     Kalifor
    -0.65
     Demokrat
    -0.65
     bakteri
    -0.65
     kompakt
    -0.64
     kooper
    -0.63
     maksi
    -0.63
    POSITIVE LOGITS
     michelin
    1.00
     peppa
    0.96
     affor
    0.96
     parma
    0.93
     scrat
    0.93
     impractica
    0.92
     intermitt
    0.91
     tupperware
    0.90
     inconce
    0.90
     unden
    0.89
    Act Density 0.221%

    No Known Activations