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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "to" along with verbs that indicate purpose or intent

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

    Followed by an infinitive

    np_acts-logits-general · gemini-2.0-flash

    purpose clauses starting with "to"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.74
    EDEFAULT
    -0.72
    rungsseite
    -0.72
     ProtoMessage
    -0.68
     GenerationType
    -0.66
     étoit
    -0.65
     ſch
    -0.64
    EndInit
    -0.64
    writeFieldEnd
    -0.63
     cref
    -0.62
    POSITIVE LOGITS
     ensure
    1.27
     avoid
    1.12
     guarantee
    1.00
     facilitate
    0.96
     prevent
    0.94
     assure
    0.92
     đảm
    0.90
     maximize
    0.89
     ensures
    0.88
    ensure
    0.87
    Act Density 0.407%

    No Known Activations