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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and other connecting words in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.89
     CreateTagHelper
    -0.82
    "])
    -0.76
    DeleteBehavior
    -0.69
    "]));
    -0.69
     дописавши
    -0.66
    Portail
    -0.65
    Filmographie
    -0.64
    hyrchwyd
    -0.61
    ()]);
    -0.61
    POSITIVE LOGITS
     whatnot
    2.03
     stuff
    1.78
     etc
    1.65
     everything
    1.61
     such
    1.59
    etc
    1.46
     whatever
    1.37
     sebagainya
    1.35
     things
    1.32
    everything
    1.32
    Act Density 0.191%

    No Known Activations