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

    Neuronpedia

    INDEX
    Explanations

    the word "typically" in various contexts

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

    how something is usually done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.55
    VersionUID
    -0.47
    aç
    -0.47
    PasswordEncoder
    -0.43
    endphp
    -0.42
     -"
    -0.42
    存于互联网档案馆
    -0.42
     zaw
    -0.42
     BoxDecoration
    -0.41
    zow
    -0.41
    POSITIVE LOGITS
     typically
    2.11
    typically
    1.86
     Typically
    1.79
    Typically
    1.78
     usually
    1.34
     normally
    1.32
    通常
    1.17
    normally
    1.17
    usually
    1.16
     ordinarily
    1.16
    Act Density 0.010%

    No Known Activations