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

    Neuronpedia

    INDEX
    Explanations

    references to reward programs and associated points or alerts

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

    travel and finance rewards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VersionUID
    -0.50
    TextAppearance
    -0.43
    нан
    -0.42
    Phone
    -0.41
     phone
    -0.40
     h
    -0.40
    Gilla
    -0.40
    IContainer
    -0.39
     Nem
    -0.39
     istore
    -0.38
    POSITIVE LOGITS
     EconPapers
    0.50
    AddTagHelper
    0.47
     itſelf
    0.44
    ⏎
    0.43
     Majefty
    0.41
     partij
    0.41
     myſelf
    0.40
    ſelf
    0.40
    ruik
    0.40
     cauſe
    0.40
    Act Density 0.008%

    No Known Activations