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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and punctuation, particularly focusing on the word 'and' as well as various forms of commas and semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.15
    2:0.06
    3:0.07
    4:0.07
    5:0.05
    6:0.06
    7:0.21
    8:0.04
    9:0.07
    10:0.08
    11:0.04
    Negative Logits
    Enough
    -2.57
    Different
    -2.43
     precon
    -2.30
    usha
    -2.30
    There
    -2.29
    du
    -2.29
    Orig
    -2.25
    Native
    -2.21
    Assuming
    -2.17
    Actually
    -2.15
    POSITIVE LOGITS
    ilial
    3.14
    mercial
    2.84
    then
    2.79
    illon
    2.73
     Shib
    2.72
    odied
    2.64
    later
    2.61
    second
    2.55
     Tackle
    2.55
    yles
    2.52
    Act Density 0.001%

    No Known Activations