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

    Neuronpedia

    INDEX
    Explanations

    dates written in text format

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.90
     manif
    -0.89
     nuts
    -0.79
     glim
    -0.77
     spit
    -0.74
     mosqu
    -0.74
     compr
    -0.73
     metic
    -0.73
     advant
    -0.72
     outsider
    -0.72
    POSITIVE LOGITS
    debian
    0.85
     Accessed
    0.83
    jpg
    0.82
     Thanks
    0.81
     Released
    0.81
     Please
    0.80
     Originally
    0.79
     Retrieved
    0.78
     Upon
    0.77
     Should
    0.77
    Act Density 0.404%

    No Known Activations