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

    Neuronpedia

    INDEX
    Explanations

    temporal references and changes in performance over time

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

    late or end time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.61
     Lordships
    -0.59
     snippetHide
    -0.55
    addCriterion
    -0.52
    뚠
    -0.51
    ↹
    -0.50
    tvguidetime
    -0.49
    msgTypes
    -0.49
    Datuak
    -0.48
    [@BOS@]
    -0.46
    POSITIVE LOGITS
     late
    0.52
    late
    0.49
    isEnd
    0.41
     LATE
    0.39
     Late
    0.39
     momentum
    0.38
    Late
    0.36
     состоя
    0.36
     cuối
    0.36
    LATE
    0.35
    Act Density 0.072%

    No Known Activations