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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" and its various grammatical forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.05
    2:0.05
    3:0.05
    4:0.06
    5:0.11
    6:0.06
    7:0.07
    8:0.23
    9:0.07
    10:0.05
    11:0.06
    Negative Logits
    terday
    -1.86
     uncons
    -1.72
    ��
    -1.71
    etheless
    -1.70
     bund
    -1.67
    ワン
    -1.65
    cht
    -1.63
    essage
    -1.62
     Enlightenment
    -1.58
    ETF
    -1.56
    POSITIVE LOGITS
    esi
    2.03
    TION
    1.81
    Spoiler
    1.69
     Indra
    1.67
    iris
    1.65
     Viz
    1.64
    asar
    1.64
    \-
    1.62
     Terran
    1.57
    ometers
    1.55
    Act Density 0.000%

    No Known Activations