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

    Neuronpedia

    INDEX
    Explanations

    quantifiers and definite articles related to groups or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.08
    3:0.07
    4:0.06
    5:0.04
    6:0.18
    7:0.21
    8:0.04
    9:0.04
    10:0.05
    11:0.11
    Negative Logits
    quartered
    -1.84
    paio
    -1.58
    haul
    -1.58
    �
    -1.58
    ��
    -1.51
     oun
    -1.50
    >[
    -1.47
     behest
    -1.46
     pilgr
    -1.46
    }}}
    -1.45
    POSITIVE LOGITS
    compatible
    1.43
    rots
    1.36
    ammers
    1.33
    ypes
    1.30
     coached
    1.25
     Ki
    1.24
     compatible
    1.22
     Chomsky
    1.22
     Harbaugh
    1.21
     nutshell
    1.18
    Act Density 0.000%

    No Known Activations