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

    Neuronpedia

    INDEX
    Explanations

    the preposition "to" indicating purpose or intent

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

    "to" followed by a verb "be"

    np_acts-logits-general · gemini-2.0-flash

    to be or to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    czego
    -0.61
    alyptus
    -0.57
    Vorte
    -0.55
    ainte
    -0.55
    يكب
    -0.54
     fince
    -0.53
    τί
    -0.52
    Hentet
    -0.52
    ardless
    -0.52
    pośred
    -0.51
    POSITIVE LOGITS
     whom
    0.86
     be
    0.83
    plevel
    0.77
    IndentedString
    0.68
    asts
    0.67
    ponym
    0.66
     Seeder
    0.64
    asting
    0.64
    pless
    0.63
     which
    0.62
    Act Density 0.438%

    No Known Activations