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

    Neuronpedia

    INDEX
    Explanations

    references to time periods or durations within a narrative

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

    durations or lengths of time

    np_acts-logits-general · gemini-2.0-flash

    durations of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    énario
    -0.56
    who
    -0.50
     прилага
    -0.50
    ンダント
    -0.49
     who
    -0.49
     lò
    -0.48
     varier
    -0.47
    unyai
    -0.47
    ConstraintMaker
    -0.47
     Who
    -0.46
    POSITIVE LOGITS
    Rüyada
    0.60
    FieldNumber
    0.58
     himſelf
    0.57
    ukone
    0.57
    مراجع
    0.55
    TagMode
    0.54
     Вікі
    0.54
     poffe
    0.52
    verifyException
    0.52
     abroad
    0.52
    Act Density 0.232%

    No Known Activations