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

    Neuronpedia

    INDEX
    Explanations

    dates written in a specific format (e.g., Month/Day/Year)

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and certain phrases in text formats, likely within dates or file references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctrl
    -0.77
    ELF
    -0.75
     glim
    -0.74
    BIL
    -0.70
    byss
    -0.69
     withd
    -0.67
    requ
    -0.65
    BAT
    -0.64
    TW
    -0.64
    elf
    -0.64
    POSITIVE LOGITS
     2010
    0.99
     2012
    0.97
     2011
    0.96
     2014
    0.96
     2008
    0.95
     2013
    0.94
     2009
    0.94
     2006
    0.93
     1998
    0.91
     2007
    0.88
    Act Density 0.098%

    No Known Activations