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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" and other associated demonstratives or pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Isles
    -0.16
    egin
    -0.15
     Crest
    -0.15
    966
    -0.15
     Morales
    -0.14
    orton
    -0.14
    olle
    -0.14
    ãĤ¤ãĥ«
    -0.14
     XmlDocument
    -0.14
    .echo
    -0.14
    POSITIVE LOGITS
    iero
    0.15
    иÑĢÑĥ
    0.14
    jid
    0.14
    éré
    0.14
     plac
    0.14
    κά
    0.14
    enames
    0.14
    iosa
    0.14
    icontrol
    0.14
     Leigh
    0.13
    Act Density 0.185%

    No Known Activations