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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iously
    -0.16
    ually
    -0.15
    onde
    -0.15
    ologically
    -0.15
     ways
    -0.15
    /
    -0.15
    (
    -0.15
    an
    -0.14
    agne
    -0.14
    ,
    -0.14
    POSITIVE LOGITS
    ched
    0.22
     same
    0.18
     statement
    0.17
     notion
    0.17
     aspect
    0.16
     же
    0.16
    ãģĿãĤĮãģ¯
    0.16
    'll
    0.15
    alone
    0.15
     scenario
    0.15
    Act Density 0.163%

    No Known Activations