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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erland
    -0.14
    "<?
    -0.14
    usher
    -0.14
    ubo
    -0.13
    ix
    -0.13
    ug
    -0.13
    {}".
    -0.13
    abus
    -0.13
    #
    -0.13
    anus
    -0.13
    POSITIVE LOGITS
    ##
    0.36
    ###
    0.29
     ##
    0.27
    ####
    0.24
    *
    0.21
     ###
    0.20
     ```↵
    0.18
     ####
    0.16
    uD
    0.16
     REFERENCES
    0.16
    Act Density 0.057%

    No Known Activations