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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     re
    -0.15
    ále
    -0.15
     Align
    -0.14
    ertain
    -0.14
     res
    -0.14
    ér
    -0.14
    æk
    -0.14
    ester
    -0.14
    ibri
    -0.14
     shall
    -0.14
    POSITIVE LOGITS
    æľį
    0.17
    UCKET
    0.16
    Ĵáŀ
    0.15
    ROTO
    0.15
    issen
    0.14
    gil
    0.14
     FindObjectOfType
    0.14
    бе
    0.14
    Mods
    0.14
    onso
    0.14
    Act Density 0.007%

    No Known Activations