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" followed by a pronoun or verb

    np_acts-logits-general · gemini-2.0-flash

    relative clauses starting with that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddWithValue
    -0.52
    quele
    -0.52
     propOrder
    -0.51
     rằng
    -0.50
    Them
    -0.48
     who
    -0.47
     vald
    -0.47
     jenem
    -0.47
    who
    -0.44
    them
    -0.44
    POSITIVE LOGITS
     we
    1.15
     they
    1.01
     you
    0.98
     he
    0.85
     everyone
    0.85
     I
    0.80
    ))^{
    0.80
     nobody
    0.79
     exists
    0.79
    '].'
    0.76
    Act Density 0.275%

    No Known Activations