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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific punctuation or formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.07
    2:0.09
    3:0.08
    4:0.08
    5:0.07
    6:0.07
    7:0.07
    8:0.09
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
    MN
    -3.01
    irtual
    -2.96
    xia
    -2.76
    opathic
    -2.66
    Rail
    -2.61
    opath
    -2.58
    trak
    -2.57
    ridor
    -2.48
    rod
    -2.45
    meal
    -2.42
    POSITIVE LOGITS
     guiActive
    2.80
     Comics
    2.75
    Reviewer
    2.58
    ®,
    2.54
     Buster
    2.51
     Wikimedia
    2.50
    }}}
    2.47
     Santa
    2.46
     Warner
    2.41
     newcom
    2.41
    Act Density 0.000%

    No Known Activations