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

    Neuronpedia

    INDEX
    Explanations

    the word "Therefore" indicating conclusions or logical connections in the text

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

    "Therefore" followed by a comma

    np_acts-logits-general · gemini-2.0-flash

    therefore,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    -0.83
    er
    -0.80
    </em>
    -0.75
    ing
    -0.70
    <strong>
    -0.67
     &
    -0.66
    бря
    -0.63
    frac
    -0.61
    al
    -0.60
    yr
    -0.60
    POSITIVE LOGITS
    verwijspagina
    1.18
    BibitemShut
    1.11
     doubtnut
    1.06
    InjectAttribute
    0.95
     nahilalakip
    0.92
     Forumite
    0.92
    theless
    0.92
     ་་
    0.90
     itſelf
    0.87
    rzost
    0.87
    Act Density 0.186%

    No Known Activations