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

    Neuronpedia

    INDEX
    Explanations

    periods at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    sentence fragments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     withd
    -1.00
     challeng
    -0.97
     glim
    -0.86
     advoc
    -0.85
    onga
    -0.78
     disadvant
    -0.78
     neighb
    -0.76
     mosqu
    -0.74
     proport
    -0.74
     thous
    -0.73
    POSITIVE LOGITS
    jpg
    1.01
    php
    0.94
    htm
    0.92
    html
    0.90
    com
    0.89
     Retrieved
    0.87
    blogspot
    0.87
    txt
    0.86
    dll
    0.85
     Originally
    0.83
    Act Density 0.199%

    No Known Activations