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

    Neuronpedia

    INDEX
    Explanations

    terms related to linguistic or semantic origins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     abbrev
    -0.16
    ioms
    -0.15
    ů
    -0.14
    erald
    -0.14
    ams
    -0.14
    amel
    -0.14
     abbreviation
    -0.14
    errupt
    -0.14
     Sentence
    -0.14
     shorthand
    -0.13
    POSITIVE LOGITS
    ãĥªãĤ«
    0.16
    istrovstvÃŃ
    0.15
    uzzi
    0.15
    «ĺ
    0.14
    rieg
    0.14
    188
    0.13
    278
    0.13
    655
    0.13
    ä¹Ī
    0.13
    appe
    0.13
    Act Density 0.046%

    No Known Activations