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

    Neuronpedia

    INDEX
    Explanations

    expressions of consistent or habitual actions and feelings

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

    Follows "always"

    np_acts-logits-general · gemini-2.0-flash

    always + verb/adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.76
    SessionFactory
    -0.73
     GenerationType
    -0.70
     måske
    -0.69
    SpringBootTest
    -0.69
     oprot
    -0.69
    出版年
    -0.69
     Lordships
    -0.68
    CloseOperation
    -0.68
    principalColumn
    -0.67
    POSITIVE LOGITS
     wondered
    0.59
    しも
    0.58
    noch
    0.58
     been
    0.55
    presence
    0.55
    cky
    0.54
     bridesmaid
    0.53
     remember
    0.49
     digo
    0.49
    engan
    0.48
    Act Density 0.086%

    No Known Activations