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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the word "that" and related conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    and
    -0.18
    ?
    -0.17
    1
    -0.17
     and
    -0.17
    3
    -0.17
    ,
    -0.17
    inand
    -0.16
    (
    -0.16
    2
    -0.16
     =
    -0.16
    POSITIVE LOGITS
     ship
    0.18
    ลาà¸Ķ
    0.17
     information
    0.17
     trend
    0.17
     process
    0.16
     info
    0.16
     endeavor
    0.16
     decision
    0.15
     idea
    0.15
     entire
    0.15
    Act Density 0.130%

    No Known Activations