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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases that indicate intentions, plans, or expectations

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

    past versus present expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GIVEREF
    -0.43
    <tbody>
    -0.41
     acoso
    -0.36
    <bos>
    -0.36
    ьаж
    -0.34
     <=",
    -0.34
    nloa
    -0.33
     misiones
    -0.32
    らしく
    -0.32
    ScopeManager
    -0.32
    POSITIVE LOGITS
    tagHelperRunner
    0.60
    verifyException
    0.59
    RegressionTest
    0.57
    transQ
    0.56
     CanadaChoose
    0.54
     الرياضيه
    0.50
    Originally
    0.48
     originally
    0.47
    原本
    0.46
    本來
    0.45
    Act Density 0.063%

    No Known Activations