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

    Neuronpedia

    INDEX
    Explanations

    long strings of numbers and mathematical symbols

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     pymysql
    -0.96
     shenan
    -0.90
     hairc
    -0.84
     paisley
    -0.82
     smtplib
    -0.80
     gaily
    -0.78
     intersper
    -0.77
     snoopy
    -0.77
     apprehen
    -0.76
     tawny
    -0.72
    POSITIVE LOGITS
     utop
    1.09
     alkoh
    0.95
     pól
    0.86
     plis
    0.83
     rú
    0.83
     diagon
    0.83
     sement
    0.83
     kosme
    0.83
     solidar
    0.82
     bont
    0.82
    Act Density 0.004%

    No Known Activations