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

    introducing consequential clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.76
     dieſen
    -0.60
     ujednoznacz
    -0.60
     contextLoads
    -0.57
     laſſen
    -0.57
    دانشنامهٔ
    -0.56
     صوتيه
    -0.56
    uxxxx
    -0.55
     viewType
    -0.55
    enumii
    -0.55
    POSITIVE LOGITS
     THAT
    0.47
     That
    0.44
    That
    0.43
     adds
    0.41
    THAT
    0.40
    that
    0.36
    adds
    0.35
    thats
    0.34
    pushFollow
    0.33
     وأن
    0.32
    Act Density 0.027%

    No Known Activations