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

    Neuronpedia

    INDEX
    Explanations

    years or dates

    oai_token-act-pair · gpt-3.5-turbo

    parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    othe
    -0.82
     glim
    -0.70
     corrid
    -0.69
     cov
    -0.67
     counter
    -0.64
     rooting
    -0.64
     shar
    -0.63
     Calm
    -0.60
     mant
    -0.60
     ranc
    -0.60
    POSITIVE LOGITS
    1995
    1.71
    1996
    1.70
    1999
    1.67
    1998
    1.67
    1994
    1.66
    1997
    1.66
    2006
    1.65
    2004
    1.64
     1995
    1.63
    2003
    1.63
    Act Density 0.093%

    No Known Activations