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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating uncertainty or future outcomes

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

    future actions and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.56
    RectangleBorder
    -0.56
    IsMutable
    -0.54
    yargs
    -0.52
    ↹
    -0.52
     CreateTagHelper
    -0.51
     plufieurs
    -0.50
     Мексичка
    -0.49
     $_(
    -0.49
     autorytatywna
    -0.48
    POSITIVE LOGITS
     会
    0.48
    会
    0.45
    都会
    0.45
     會
    0.41
     sẽ
    0.38
    就会
    0.38
    .(*
    0.36
    Will
    0.35
     will
    0.35
     Will
    0.34
    Act Density 0.038%

    No Known Activations