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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty about timing

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

    too early or too young

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AttributeSet
    -0.28
     ה
    -0.28
     med
    -0.28
     instead
    -0.27
     increased
    -0.27
     itse
    -0.27
     weak
    -0.27
    aClass
    -0.25
    XtraReports
    -0.24
     non
    -0.24
    POSITIVE LOGITS
    [@BOS@]
    0.78
    <pad>
    0.78
    <unused79>
    0.78
    <unused52>
    0.78
    <unused16>
    0.78
    <unused28>
    0.78
    <unused41>
    0.77
    <unused80>
    0.77
    <unused3>
    0.77
    <unused8>
    0.77
    Act Density 0.006%

    No Known Activations