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

    Neuronpedia

    INDEX
    Explanations

    quotations and punctuation marks indicating dialogue or speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nist
    -0.15
     ("-
    -0.15
     addCriterion
    -0.15
    ï¼Į请
    -0.14
     Sphere
    -0.14
    $fdata
    -0.14
    ãģ£ãģ¡
    -0.14
    ãĤ¹ãĥŀ
    -0.14
    zeÅĦ
    -0.14
    _vlog
    -0.14
    POSITIVE LOGITS
     [
    0.29
    :↵
    0.19
    -↵
    0.19
     Dear
    0.17
     "
    0.16
     there
    0.15
     "[
    0.15
     {{{
    0.15
    âĢ¦
    0.15
    447
    0.15
    Act Density 0.160%

    No Known Activations