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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official documentation or policy

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     withd
    -0.91
     glim
    -0.90
     challeng
    -0.85
     manif
    -0.77
     advoc
    -0.77
     mosqu
    -0.76
     disadvant
    -0.73
     advis
    -0.73
    onga
    -0.73
     explan
    -0.71
    POSITIVE LOGITS
    jpg
    1.12
    php
    1.06
    htm
    1.04
    txt
    1.04
    html
    1.04
    com
    0.96
    png
    0.93
    blogspot
    0.92
    pdf
    0.91
    dll
    0.90
    Act Density 0.184%

    No Known Activations