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

    Neuronpedia

    INDEX
    Explanations

    references to logging and log files

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Majefty
    -1.23
    ########.
    -1.17
     $_"
    -1.17
     pleaſure
    -1.17
     myſelf
    -1.11
     Monfieur
    -1.10
     Jefus
    -1.07
     Diſ
    -1.06
     Inſ
    -1.06
     Houſe
    -1.05
    POSITIVE LOGITS
     log
    1.31
    log
    1.25
     Log
    1.20
    Log
    1.18
    Slf
    1.15
     logs
    1.12
     LOG
    1.11
     Logs
    1.08
    LOG
    1.02
    Logs
    0.93
    Act Density 0.018%

    No Known Activations