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

    introduces clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.72
    UrlResolution
    -0.63
     propOrder
    -0.52
     Wiktionnaire
    -0.52
    WebElementEntity
    -0.51
     فريبيس
    -0.51
    ChildScrollView
    -0.50
    AISSEE
    -0.50
    Bioaccumulative
    -0.49
    FormUrlEncoded
    -0.48
    POSITIVE LOGITS
     Daß
    0.56
     daß
    0.56
     bahwa
    0.52
    That
    0.50
    that
    0.50
    dat
    0.48
    Dat
    0.45
     وأن
    0.45
     rằng
    0.44
    THAT
    0.44
    Act Density 0.039%

    No Known Activations