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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    that introducing clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iostream
    -0.41
     poupée
    -0.38
     spørs
    -0.36
     intérieure
    -0.36
     coopération
    -0.36
     judiciaire
    -0.35
     forensic
    -0.34
     aérienne
    -0.34
     spirituale
    -0.34
     the
    -0.34
    POSITIVE LOGITS
    THAT
    0.87
     that
    0.87
    that
    0.84
     THAT
    0.81
    That
    0.78
     που
    0.78
     والتي
    0.75
     tht
    0.75
     That
    0.75
     que
    0.72
    Act Density 0.168%

    No Known Activations