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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific punctuation marks and certain words related to speech or communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.19
    1:0.09
    2:0.09
    3:0.05
    4:0.04
    5:0.03
    6:0.07
    7:0.11
    8:0.04
    9:0.06
    10:0.14
    11:0.04
    Negative Logits
     Haj
    -3.66
     ACE
    -2.98
     Drupal
    -2.96
     Ka
    -2.92
    mx
    -2.80
    UTC
    -2.79
     Maul
    -2.78
    eur
    -2.77
    Torrent
    -2.76
     Kah
    -2.74
    POSITIVE LOGITS
     Lily
    8.14
     Lilly
    6.76
     Lori
    3.85
     Snape
    3.67
     Severus
    3.58
    iri
    3.43
     Lis
    3.35
     Fiona
    3.33
     Lup
    3.33
     Lys
    3.27
    Act Density 0.001%

    No Known Activations